SkillNavora Study Library

Learn the skills, tools and AI workflows to solve real product problems, build a portfolio with 25+ case studies and crack your next PM interview.

What you will be able to do

• Run discovery and turn research into clear problem statements
• Prioritise, write PRDs and user stories, and align stakeholders
• Plan sprints and ship with Jira, Confluence and Asana
• Define metrics, read funnels, write SQL and run A/B tests
• Design and ship AI features: LLMs, RAG, agents, evals and guardrails
• Build and launch your own website and AI prototype with Claude Code, Figma and Lovable
• Build a portfolio of 25+ case studies and a capstone
• Crack PM interviews with mock tests and 1:1 mock interviews

Curriculum

1. Product thinking and the PM role
   What PMs do and how they decide · Product life cycle and delivery approaches (Agile, Scrum, Kanban) · Outcomes over output · Types of PM roles: B2C, B2B SaaS, platform, growth, AI PM
2. Product strategy
   Vision, positioning and moats · Market sizing (TAM, SAM, SOM) and competitor analysis · Business models and pricing · OKRs and outcome roadmaps
3. Discovery and user research
   User interviews and surveys · Jobs-to-be-done, personas and journey maps · Synthesis and insights · Research tools: Google Forms, Typeform, Dovetail, Hotjar, Microsoft Clarity
4. Problem framing and prioritisation
   Root-cause analysis: five whys, fishbone · RICE, Kano, MoSCoW and value vs effort · MVPs and experiment design · Opportunity solution trees
5. UX, wireframes and Figma
   UX principles and design reviews · Wireframes and prototypes in Figma and FigJam · Usability testing · Working with designers; Balsamiq and Miro for quick sketches
6. PRDs, user stories and documentation
   Writing PRDs and one-pagers · User stories and acceptance criteria · Confluence and Notion for product docs · Writing PRDs with AI and getting them critiqued
7. Agile delivery with Jira, Confluence and Asana
   Backlogs, epics, sprints and boards in Jira · Sprint planning, stand-ups and retros · Roadmaps and cross-team projects in Asana · Release notes and stakeholder updates; Linear, Trello and ClickUp compared
8. Analytics, SQL and experimentation
   North-star, input and guardrail metrics · Funnels, cohorts and retention in Mixpanel, Amplitude and GA4 · SQL for PMs and Excel / Google Sheets · Dashboards in Looker Studio; A/B testing and statistics basics
9. Launch, growth and monetisation
   Go-to-market planning · Growth loops, activation and retention · Pricing and packaging · Launch checklists and post-launch reviews
10. Tech and system design for PMs
    How the web works: front end, back end, APIs and databases · Testing APIs with Postman · Cloud, scalability and trade-offs · Explaining systems in interviews
11. AI foundations for PMs
    How LLMs work: tokens, context, hallucinations · Prompt engineering · RAG, embeddings and vector search · Evaluations, cost, latency, risk and responsible AI
12. Claude for product managers
    Claude Projects for research, synthesis and PRDs · Artifacts: dashboards, mock-ups and documents · Connectors: Gmail, Calendar, Drive, Slack and GitHub · Skills and MCP: connecting Claude to your own tools
13. Claude Code: build and launch a website
    Setting up Claude Code and GitHub · Building a landing page or product website from a prompt · Deploying free on Cloudflare Pages or Netlify, with your own domain · Adding forms, analytics and an AI chatbot; iterating safely with Git
14. AI prototyping and automation tools
    Lovable, Bolt, v0 and Replit for app prototypes · Figma Make and AI design tools · n8n, Zapier and Make automations · ChatGPT, Gemini, Perplexity and NotebookLM for research
15. Agentic AI and AI product design
    Agents, tool use and MCP · Human-in-the-loop and guardrails · AI metrics and evaluation · Writing an AI PRD
16. AI evals: measuring AI quality (basic to advanced)
    What evals are and why PMs own them; success criteria and rubrics · Golden datasets, code graders, human review and LLM-as-judge · Error analysis, RAG and agent evals, safety and red-teaming · A/B tests, monitoring, regression gates and the eval section of an AI PRD
17. Prompt and context engineering
    Evidence-based requests: goal, audience, context, constraints, format, quality bar · Structured outputs, task decomposition and chaining · Long-context compression, documents, PDFs and OCR · Source attribution, fact-checking and knowledge graphs
18. AI skills and templates for PM work
    Skills vs tools vs memory vs evals · Claude Agent Skills, Projects, Custom GPTs and Gems · A PM skill library: PRDs, updates, teardowns, metrics · Project: case study → PRD → presentation skill with evals
19. Browser automation and AI agents
    Scripts, RPA and AI browser agents: when to use which · Playwright basics and Chrome Recorder for PMs · Computer-use agents, deep research agents and competitor research · Safety, approvals, prompt injection and evaluating browser agents
20. Your AI second brain and context engineering
    PARA and CODE: capture, organise, distil, express · NotebookLM, Claude Projects, Notion AI and Obsidian · Context engineering and managing AI memory · Insight repository, decision log and MCP-connected knowledge
21. Agent orchestration and monitoring
    Workflows vs agents; chaining, routing and parallel work · Orchestrator-workers, evaluator-optimizer and multi-agent systems · State, checkpoints, approvals and error recovery · Triggers, cost control and production monitoring
22. AI builder tools: Claude, ChatGPT & Codex, Gemini, Lovable
    What each AI tool can do and when to use it · Claude Projects, Artifacts and connectors; ChatGPT Projects, Canvas and custom GPTs; Gemini, Gems and NotebookLM · Build and publish a website with Lovable, Claude Code or Codex on your own domain · Connect your tools and other websites: Zapier, Make, n8n, webhooks, APIs, payments
23. Web automation: webhooks, triggers and Playwright MCP
    Webhooks: receive events securely (signatures, idempotency, retries) · Triggers: schedules (cron), events, polling and manual · Browser automation with Playwright; Playwright MCP with Claude · Other platforms: Selenium, Puppeteer, Browser Use, Stagehand, Apify, n8n, Zapier, Make, RPA
24. Advanced AI product management
    AI product strategy: moats, data flywheels, build vs buy vs partner · Designing AI experiences (AI UX) and pricing AI products · ML products for PMs, AI governance and responsible AI · Platform & API product management, product operations, multimodal AI
25. Capstone, mock tests and interview preparation
    Capstone: build and pitch your own AI product · Weekly mock tests · Product sense, metrics, strategy, RCA and behavioural rounds · 1:1 mock interviews with feedback
26. Job assistance program
    Resume and LinkedIn makeover · Portfolio of 25+ case studies · Referrals and job-search strategy · Offer negotiation and salary discussions

Learn SQL, Python, data modelling, pipelines, Spark, Airflow and the cloud, then build the data and AI pipelines that power modern products.

What you will be able to do

• Write advanced SQL and production-quality Python for data
• Design data models and warehouses (star schema, lakehouse)
• Build batch and streaming pipelines with Spark, Airflow, dbt and Kafka
• Run data on the cloud with Snowflake, BigQuery or Databricks
• Build AI data pipelines: embeddings, vector databases and RAG
• Ship a portfolio-grade end-to-end data platform

Curriculum

1. SQL for data engineers
   Joins, window functions and CTEs · Query performance and indexes · SQL interview patterns
2. Python for data engineering
   Python for files, APIs and automation · pandas and Polars · Testing and packaging code
3. Data modelling and warehousing
   OLTP vs OLAP · Star and snowflake schemas · Slowly changing dimensions
4. ETL and ELT pipelines
   Batch ingestion from APIs and databases · Transformations with dbt · Incremental loads and idempotency
5. Orchestration with Airflow
   DAGs, scheduling and retries · Backfills and dependencies · Monitoring and alerting
6. Big data with Spark
   Spark and PySpark basics · Partitioning and performance · Lakehouse with Delta Lake
7. Streaming data
   Kafka fundamentals · Real-time pipelines · Exactly-once and late data
8. Cloud data platforms
   AWS, GCP and Azure data services · Snowflake, BigQuery and Databricks · Cost, security and access control
9. Data quality and governance
   Data tests and contracts · Lineage and observability · Privacy and compliance
10. AI for data engineers
    Embeddings and vector databases · RAG and LLM data pipelines · AI-assisted coding with Claude Code
11. Capstone, interviews and job assistance
    End-to-end data platform capstone · SQL, Python and system design mock interviews · Resume, portfolio and referrals

A beginner-friendly program to use generative AI at work: prompting, AI assistants, no-code apps, automations, chatbots and voice agents.

What you will be able to do

• Write prompts that get reliable results
• Use Claude daily for writing, research and analysis
• Build a website or web app without code
• Automate repetitive work with n8n or Zapier
• Launch a WhatsApp or website chatbot
• Use AI responsibly and safely

Curriculum

1. How generative AI works
   LLMs in plain language · What AI is good and bad at · Choosing the right tool
2. Prompting that works
   Clear instructions and examples · Roles, formats and constraints · Checking and improving answers
3. AI assistants for daily work
   Claude Projects · Research and analysis · Docs, emails and presentations
4. Websites and no-code apps
   Lovable from prompt to app · Building a website with Claude · Publishing with your own domain
5. Automation
   Zapier and Make basics · n8n with AI steps · Email and sheet workflows
6. Chatbots and voice agents
   WhatsApp and website bots · Voice receptionists · Handoff to humans
7. Prompt and context engineering
   Evidence-based requests and structured outputs · Breaking big tasks into steps · Reading documents, PDFs and scans with AI
8. AI skills and templates
   Custom GPTs, Gems, Claude Projects and Skills · Templates for documents you write every week · Testing a skill so it stays reliable
9. AI agents, MCP and deep research
   What AI agents are and how they use tools · MCP: connecting AI to your apps · Deep research agents and checking sources
10. Browser automation and AI agents
    No-code record-and-replay and AI browser agents · Writing safe agent tasks with stop points · Real workflows: research, forms, price tracking
11. Your AI second brain
    PARA and CODE with Notion, Obsidian or NotebookLM · Context engineering and AI memory · Automating notes from meetings, email and reading
12. AI evals: checking AI quality
    What evals are and simple rubrics · Test sets and AI-as-judge · Safety checks and monitoring
13. Agent orchestration and monitoring
    Workflows vs agents and simple patterns · Approvals, retries and schedules · Cost control and monitoring
14. AI builder tools: Claude, ChatGPT, Gemini, Lovable
    Pick the right AI tool for each task · Create a website and add pages with Lovable or Claude Code · Connect forms, sheets, WhatsApp and other websites
15. Web automation: webhooks, triggers and Playwright MCP
    What webhooks and triggers are, with no-code examples · Let Claude use a browser with the Playwright MCP · Automate with n8n, Zapier or Make
16. AI strategy, AI UX, governance and AI media
    Where AI creates value and choosing tools · Designing AI experiences people trust · Responsible AI and data protection · Images, voice and video with AI
17. Responsible AI
    Privacy and data safety · Bias and accuracy · Company AI policies
18. Capstone
    Solve a real problem with AI · Demo day · Certificate

From the Excel window to dashboards: formatting, 100+ functions, lookups, pivot tables, advanced charts, Power Query, Power Pivot and AI in Excel.

1. 1. Getting Started with Excel for Data Analysis Beginner 90 min
   Learn the Excel window, the words analysts use every day, how to lay out data so it can be analysed, the five data types Excel understands, and the shortcuts that save hours.
   • Name every part of the Excel window and explain what it does
   • Use the core vocabulary (workbook, worksheet, cell, range, reference, formula, function) correctly
   • Recognise structured data and fix a badly laid-out sheet
   PDF: download
2. 2. Data Entry, Data Validation & Data Cleaning Beginner 90 min
   Stop bad data at the door with data validation and drop-down lists, then clean what already exists with Flash Fill, Text to Columns, Find & Replace, Go To Special, Remove Duplicates, Paste Special and Excel Tables.
   • Enter data quickly and consistently with AutoFill, Flash Fill and custom lists
   • Build drop-down lists, number and date limits and custom-formula rules with Data Validation
   • Create dependent (cascading) drop-downs
   PDF: download
3. 3. Number, Custom & Conditional Formatting Beginner 100 min
   Make numbers readable and insights jump out. Learn cell and number formats, write your own custom number formats (including lakhs and crores, K and M, and colour codes), and use conditional formatting with built-in rules and your own formulas.
   • Apply cell formatting (fonts, alignment, borders, wrap, merge alternatives) the professional way
   • Choose the right built-in number format and know that formatting never changes the stored value
   • Write custom number formats with sections, conditions, colours, text and scaling
   PDF: download
4. 4. Formulas, Cell References & Aggregate Functions Beginner 110 min
   Write formulas with confidence. Understand operators and their order, relative, absolute and mixed references, and every aggregate function you need, from SUM and COUNTA to SMALL, LARGE, SUMIFS, COUNTIFS, MAXIFS, SUBTOTAL and AGGREGATE.
   • Explain the difference between a formula and a function and read any function's syntax
   • Predict how a formula changes when copied, and lock references with $ (F4)
   • Summarise data with SUM, COUNT, COUNTA, COUNTBLANK, AVERAGE, MIN, MAX, SMALL, LARGE, MEDIAN and MODE
   PDF: download
5. 5. Text Functions, Logical Functions & IF Beginner 120 min
   Extract, clean, combine and reformat text with LEFT, RIGHT, MID, LEN, FIND, SEARCH, CONCAT, TEXTJOIN, TEXT and the new TEXTSPLIT/TEXTBEFORE/TEXTAFTER. Then make decisions with AND, OR, NOT, IF, nested IF, IFS, SWITCH and IFERROR.
   • Extract parts of codes, names and emails with LEFT, RIGHT, MID, FIND and SEARCH
   • Combine text with &, CONCAT and TEXTJOIN and format numbers inside text with TEXT
   • Split text with Text to Columns and the TEXTSPLIT, TEXTBEFORE and TEXTAFTER functions
   PDF: download
6. 6. Sorting, Filtering & Dynamic Arrays Beginner–Intermediate 110 min
   Organise data with single and multi-level sorts and custom orders, find what matters with AutoFilter and Advanced Filter, and then let formulas do it for you with the dynamic array functions UNIQUE, SORT, SORTBY, FILTER and SEQUENCE, plus the power tool SUMPRODUCT.
   • Sort by one or many levels, by custom lists, by colour and left to right
   • Filter text, numbers and dates, and use Advanced Filter with AND/OR criteria ranges
   • Explain spill ranges, the # operator and the #SPILL! error
   PDF: download
7. 7. Lookup Functions: VLOOKUP, XLOOKUP and INDEX-MATCH Intermediate 120 min
   Bring data together from different tables. Master VLOOKUP and HLOOKUP (exact and approximate match), the modern XLOOKUP, the flexible INDEX + MATCH combination (including two-way and reverse lookups), OFFSET, consolidating several sheets, CHOOSE, and how to troubleshoot #N/A.
   • Explain why lookups are the Excel equivalent of a SQL join
   • Use VLOOKUP and HLOOKUP with exact and approximate match, and know their limits
   • Use XLOOKUP for left lookups, default values, last-match search and multiple return columns
   PDF: download
8. 8. Pivot Tables from Basic to Advanced Intermediate 150 min
   Summarise thousands of rows in seconds. Build pivot tables, understand the pivot cache and the four areas, change value field settings, show values as % of total, MoM and YoY change and running totals, group dates and numbers into bins, add calculated fields, slicers and timelines, and solve the Video Game Sales case study.
   • Build a pivot table and explain the pivot cache, the four areas and Refresh vs Refresh All
   • Change the summary function and number format, and show values as % of total, % of row and running totals
   • Calculate month-on-month (MoM) and year-on-year (YoY) change
   PDF: download
9. 9. Date, Time & Number Functions and Named Ranges Intermediate 120 min
   Work confidently with dates and times (DATE, EOMONTH, EDATE, WORKDAY, NETWORKDAYS, WEEKDAY, WEEKNUM, DATEDIF, fiscal quarters), clean up numbers with INT, MOD, ROUND, CEILING and FLOOR, and make formulas readable with static and dynamic named ranges and LET.
   • Explain how Excel stores dates and times, and do date arithmetic correctly
   • Extract parts of dates, find month ends, add months, and count working days with holidays
   • Calculate age, tenure and fiscal-year quarters (Indian April–March and US October–September)
   PDF: download
10. 10. Charts and Advanced Charts Intermediate 130 min
    Choose the right chart for every question, build and format column, bar, line, area, pie, scatter and combo charts, add sparklines, and create the advanced business charts taught in class: thermometer, Pareto, population pyramid and waterfall, plus histogram, box plot, treemap and funnel.
    • Pick the right chart type from the question you want to answer
    • Insert, edit and format charts quickly (elements, axes, labels, colours, templates)
    • Build combo charts with a secondary axis and add sparklines
    PDF: download
11. 11. Interactive Dashboard: Superstore Case Study Intermediate–Advanced 150 min
    Build a complete, interactive sales dashboard from the Superstore data, from business questions and KPIs to pivot charts, slicers, a timeline, KPI cards and a dynamic title. Then protect it (sheet, workbook, allowed ranges), document it with comments and notes, and audit formulas with Evaluate Formula.
    • Turn a business brief into KPIs and questions before building anything
    • Prepare data, create one pivot per visual and connect them with slicers and a timeline
    • Build KPI cards and a dynamic title with GETPIVOTDATA and TEXT
    PDF: download
12. 12. Power Query, Power Pivot, Analysis ToolPak & What-If Analysis Advanced 150 min
    Automate cleaning with Power Query (import, transform, unpivot, merge, append, group), model several tables with Power Pivot and DAX, get descriptive statistics and regression from the Analysis ToolPak, plan with Goal Seek, Data Tables, Scenario Manager and Solver, and meet LAMBDA, Python in Excel and macros.
    • Build repeatable ETL in Power Query and explain the Applied Steps and M code
    • Unpivot wide data, merge (join) and append (union) tables, and group data in Power Query
    • Load tables to the Data Model, create relationships and write simple DAX measures in Power Pivot
    PDF: download

Relational databases, ER diagrams and keys, DDL/DML, filtering, aggregation, joins, set operators, subqueries, window functions, CTEs, views, procedures and performance.

1. 1. Databases, RDBMS & SQL Basics Beginner 100 min
   Understand what a database is, how relational databases organise data into tables, the vocabulary of SQL, the four families of SQL statements (DDL, DML, DCL, TCL), how SQL compares with Excel, and how to install SQL Server and SSMS and run your first query.
   • Explain what a database, a DBMS and an RDBMS are and why companies use them instead of spreadsheets
   • Use the core vocabulary (table, row/record, column/field, schema, query, result set)
   • Classify SQL statements into DDL, DML, DQL, DCL and TCL
   PDF: download
2. 2. ER Diagrams, Relationships, Keys & Normalisation Beginner 110 min
   Design databases the way professionals do. Draw ER diagrams, read crow's-foot notation, model one-to-one, one-to-many and many-to-many relationships, master every type of key (super, candidate, primary, alternate, composite, foreign, surrogate) and normalise tables to 3NF.
   • Read and draw an ER diagram with entities, attributes and relationships
   • Identify 1:1, 1:N and M:N relationships and resolve M:N with a junction table
   • Define super, candidate, primary, alternate, composite, foreign, surrogate and unique keys, with examples
   PDF: download
3. 3. Data Types, Operators, NULLs, Variables & Comments Beginner 100 min
   Choose the right SQL Server data type for every column, use arithmetic, comparison, logical and string operators correctly, understand NULL and three-valued logic, declare variables, follow naming rules and write readable, commented SQL.
   • Pick suitable numeric, text, date/time and other data types, and know why the choice matters
   • Use arithmetic, comparison, logical and concatenation operators, including integer division and modulo
   • Explain NULL, three-valued logic, IS NULL and COALESCE
   PDF: download
4. 4. DDL, DML & Constraints: CREATE, ALTER, INSERT, UPDATE, DELETE Beginner 120 min
   Create and change tables with DDL (CREATE, ALTER, DROP, TRUNCATE), add, change and remove rows with DML (INSERT, UPDATE, DELETE, MERGE), protect data quality with constraints (PRIMARY KEY, FOREIGN KEY, UNIQUE, NOT NULL, CHECK, DEFAULT, IDENTITY) and understand DELETE vs TRUNCATE vs DROP.
   • Create databases and tables with appropriate data types and constraints
   • Modify table structure with ALTER TABLE (add, change, drop columns and constraints)
   • Insert single and multiple rows, insert from a query, update and delete rows safely
   PDF: download
5. 5. SELECT, WHERE, ORDER BY & Filtering Operators Beginner 120 min
   Retrieve exactly the rows and columns you need. Master SELECT, aliases with AS, DISTINCT, TOP, WHERE with comparison and logical operators, IN, BETWEEN, LIKE wildcards, IS NULL, ORDER BY, and the logical order in which SQL processes a query.
   • Select columns, calculated expressions and aliases, and remove duplicates with DISTINCT
   • Filter rows with comparison, logical, IN, NOT IN, BETWEEN, LIKE, NOT LIKE, IS NULL and IS NOT NULL
   • Sort results by one or more columns, expressions and positions; limit rows with TOP
   PDF: download
6. 6. SQL Functions: Aggregate, Text, Date & Number Beginner–Intermediate 120 min
   Use SQL Server's built-in functions to summarise, clean and reshape data. Aggregate functions (COUNT, SUM, AVG, MIN, MAX, STRING_AGG), text functions (LEN, LEFT, RIGHT, SUBSTRING, CHARINDEX, REPLACE, TRIM, UPPER, CONCAT), date functions (GETDATE, YEAR, MONTH, DATEPART, DATENAME, DATEADD, DATEDIFF, EOMONTH) and number functions (ROUND, CEILING, FLOOR, ABS, POWER, SQRT), plus CAST and CONVERT.
   • Distinguish scalar functions (one value per row) from aggregate functions (one value per group)
   • Summarise data with COUNT(*), COUNT(column), COUNT(DISTINCT), SUM, AVG, MIN, MAX and STRING_AGG
   • Clean and extract text with LEN, LEFT, RIGHT, SUBSTRING, CHARINDEX, REPLACE, TRIM, UPPER, LOWER and CONCAT
   PDF: download
7. 7. GROUP BY, HAVING, CASE WHEN, ROLLUP, CUBE & COALESCE Intermediate 130 min
   Turn rows into business summaries. Group with GROUP BY, filter groups with HAVING, create conditional columns and buckets with CASE WHEN, pivot data with conditional aggregation, and add subtotals and grand totals with ROLLUP, CUBE and GROUPING SETS, cleaning the labels with COALESCE and GROUPING().
   • Summarise data by one or more columns with GROUP BY and aggregate functions
   • Filter groups with HAVING and explain WHERE vs HAVING
   • Create conditional columns and buckets with CASE WHEN … THEN … ELSE … END
   PDF: download
8. 8. Joins and a Retail Case Study Intermediate 150 min
   Combine tables with INNER, LEFT, RIGHT, FULL OUTER, CROSS and SELF joins, find missing matches with anti-joins, avoid the classic join mistakes (row explosion, filters in ON vs WHERE), and answer a full set of business questions on the retail database.
   • Explain each join type with a Venn picture and predict how many rows it returns
   • Write INNER, LEFT, RIGHT, FULL OUTER, CROSS and SELF joins with table aliases
   • Find unmatched rows with LEFT JOIN … IS NULL (anti-join)
   PDF: download
9. 9. Set Operators: UNION, UNION ALL, INTERSECT & EXCEPT Intermediate 80 min
   Stack and compare query results. Append data with UNION ALL, remove duplicates with UNION, find common rows with INTERSECT and differences with EXCEPT, follow the rules for compatible columns, and know when to use a set operator instead of a join.
   • Explain the difference between joins (add columns) and set operators (add or compare rows)
   • Append results with UNION ALL and de-duplicate with UNION
   • Find common rows with INTERSECT and missing rows with EXCEPT
   PDF: download
10. 10. Subqueries, Derived Tables & EXISTS Intermediate 120 min
    Put queries inside queries. Use scalar subqueries, multi-row subqueries with IN, ANY and ALL, correlated subqueries, EXISTS and NOT EXISTS, and derived tables (inline views) to answer questions that one level of SELECT cannot, and learn when a join, CTE or window function is better.
    • Identify scalar, multi-row, multi-column and table subqueries and where each can be used
    • Filter with subqueries using comparison operators, IN, NOT IN, ANY and ALL
    • Write correlated subqueries and explain how they are evaluated
    PDF: download
11. 11. OFFSET-FETCH and Window Functions I: OVER, PARTITION BY & Ranking Intermediate–Advanced 130 min
    Page through results with OFFSET and FETCH, then learn window functions, the most powerful analytics feature in SQL. Understand OVER and PARTITION BY, rank rows with ROW_NUMBER, RANK, DENSE_RANK and NTILE, solve top-N-per-group and de-duplication problems, and compare aggregate windows with GROUP BY.
    • Paginate with ORDER BY … OFFSET … ROWS FETCH NEXT … ROWS ONLY
    • Explain what a window function is and how OVER, PARTITION BY and ORDER BY define the window
    • Use ROW_NUMBER, RANK, DENSE_RANK and NTILE and explain how ties behave
    PDF: download
12. 12. Window Functions II: Running Totals, LEAD, LAG & Frames Advanced 130 min
    Build time-series analytics in SQL. Use window frames (ROWS BETWEEN) for running totals and moving averages, LAG and LEAD for month-on-month and year-on-year growth, FIRST_VALUE and LAST_VALUE, cumulative percentages, PERCENT_RANK, CUME_DIST and PERCENTILE_CONT, and gaps-and-islands patterns.
    • Define a window frame with ROWS BETWEEN and explain the default frame when ORDER BY is present
    • Calculate running totals, moving averages and cumulative shares
    • Compare each row with the previous or next row using LAG and LEAD (MoM, YoY, gaps)
    PDF: download
13. 13. CTEs, Views, Temporary Tables, Stored Procedures & Functions Advanced 130 min
    Write queries other people can read and reuse. Use CTEs (including recursive CTEs for hierarchies and calendars), create views for reusable logic and security, use temp tables and table variables, and build stored procedures, user-defined functions, parameters and basic error handling in T-SQL.
    • Structure complex queries with one or more CTEs and explain CTE vs subquery vs temp table
    • Write recursive CTEs for hierarchies (org charts) and number or date series
    • Create, alter and use views, and explain what views are good for
    PDF: download
14. 14. Transactions, Indexes, Performance & Security Advanced 110 min
    Make SQL safe and fast. Understand transactions and ACID (BEGIN, COMMIT, ROLLBACK, SAVE), isolation and locking, indexes (clustered, non-clustered, covering), how to read an execution plan, a checklist for writing fast queries, and permissions with GRANT, REVOKE and roles (DCL).
    • Explain ACID and group statements into transactions that commit or roll back together
    • Describe isolation levels, locks, blocking and deadlocks at an analyst level
    • Choose between clustered and non-clustered indexes and recognise queries that can or cannot use them
    PDF: download
15. 15. End-to-End SQL Case Study & Interview Practice Advanced 180 min
    Put everything together. Work through a complete analysis of the retail business (data quality, KPIs, trends, customer segmentation, retention, product and discount analysis) using joins, CTEs and window functions, then practise 25 classic SQL interview questions with model answers.
    • Run a structured SQL analysis: understand the data, check quality, calculate KPIs, find drivers, and recommend actions
    • Combine joins, CTEs, aggregation and window functions in multi-step queries
    • Build customer segments (RFM), cohort and retention views in SQL
    PDF: download

ETL with Power Query, star-schema modelling, DAX measures and time intelligence, interactive reports, case studies, publishing, security and Copilot.

1. 1. Getting Started with Power BI & Your First HR Report Beginner 120 min
   Understand what Power BI is and how its parts fit together, install Power BI Desktop, tour the three views, follow the ETL and analytics stages, and build a complete first report on HR data: cards, bar and column charts, a donut, slicers, a year column with DAX, groups and small multiples.
   • Describe Power BI Desktop, the Service and Mobile, and how data flows between them
   • Explain ETL and the stages of the data-analytics process, and map them to Power BI tools
   • Navigate Report, Table and Model views, and the Fields, Visualizations and Filters panes
   PDF: download
2. 2. Power Query, Star Schema & Data Modelling (Adventure Cycles) Intermediate 140 min
   Prepare and model data the professional way. Clean data in Power Query, load a star schema (fact and dimension tables), create one-to-many relationships, understand filter direction, build and mark a date table, create hierarchies, and avoid the most common modelling mistakes, using the Adventure Cycles case study.
   • Apply common Power Query steps and read the Applied Steps and M code
   • Explain fact tables, dimension tables and the star schema, and why they beat one wide table
   • Create relationships with the right cardinality and filter direction, and explain how filters flow
   PDF: download
3. 3. DAX Fundamentals: Measures, Filter Context & CALCULATE Intermediate 150 min
   Learn DAX, the formula language of Power BI. Understand calculated columns vs measures, row context vs filter context, write core aggregations and iterators (SUMX), master CALCULATE and FILTER, ALL/REMOVEFILTERS and ALLSELECTED, handle division safely, use variables, and build a library of business measures.
   • Explain the difference between a calculated column and a measure, and when to use each
   • Describe row context and filter context and predict what a measure returns in a visual
   • Write aggregation measures and iterators (SUM, COUNTROWS, DISTINCTCOUNT, SUMX, AVERAGEX)
   PDF: download
4. 4. DAX Time Intelligence, Ranking, Parameters & Dynamic Measures Advanced 150 min
   Make dashboards answer "compared with when?". Build year-to-date, month-to-date, same-period-last-year, month-on-month and year-on-year measures, rolling averages, rankings with RANKX and TOPN, what-if parameters, field parameters and dynamic measure switching, and know visual calculations and calculation groups.
   • Explain what time intelligence needs (a marked date table) and use TOTALYTD, DATESYTD, SAMEPERIODLASTYEAR, DATEADD and PARALLELPERIOD
   • Build YoY %, MoM %, YTD, rolling 3-month and running-total measures
   • Rank items with RANKX and show the Top N with TOPN, including an "Others" bucket
   PDF: download
5. 5. Visuals, Filters, Drill-through, Tooltips, Buttons & Report Design Intermediate 150 min
   Turn a model into an interactive, well-designed report. Choose visuals, format them (cards, matrix, charts, gauge, KPI, maps, images), use visual, page and report filters, edit interactions, drill-down and drill-through, custom tooltips, bookmarks and buttons, conditional formatting, themes and design principles.
   • Pick the right visual for each question and configure its field wells and formatting
   • Apply visual, page and report-level filters, Top N, relative date filters and slicer sync
   • Control cross-filtering with Edit interactions; add drill-down, drill-through and report-page tooltips
   PDF: download
6. 6. Power BI Service, Connectivity Modes, Security & Capstone Advanced 150 min
   Take a report from Desktop to the people who need it. Understand Import, DirectQuery, Live connection, composite models and Direct Lake, publish to the Service, schedule refresh with a gateway, share through workspaces and apps, secure data with row-level security, tune performance, work with Copilot and Fabric, and complete the Adventure Cycles capstone.
   • Compare Import, DirectQuery, Live connection, Composite and Direct Lake modes and choose one
   • Publish a report, configure scheduled refresh and a gateway, and share via workspaces, apps and links
   • Implement and test row-level security (static and dynamic) with DAX filters
   PDF: download

Tableau Public and Desktop: connecting data, dimensions and measures, every core chart, calculated fields, table calculations and LOD expressions, filters, parameters and sets, data modelling, dashboards, stories and publishing.

1. 1. Getting Started with Tableau: Interface, Data Connections and Your First Views Beginner 120 min
   Understand the Tableau product family, install Tableau Public, connect to the Superstore India data, read the Data Source page, learn dimensions vs measures and discrete vs continuous fields, master the Marks card and shelves, build and sort your first views, and save them to Tableau Public.
   • Describe Tableau Desktop, Public, Cloud, Server, Prep and Pulse, and when each is used
   • Connect to a CSV, check data types and rename or hide fields on the Data Source page
   • Explain dimensions vs measures and discrete (blue) vs continuous (green) fields
   PDF: download
2. 2. Charts in Tableau: From Bar and Line to Maps, Dual Axis, Histograms and Pareto Beginner 150 min
   Build every core chart in Tableau and know when to use each: bar, stacked and side-by-side bars, line and area, pie and donut, treemap, highlight table, scatter plot, histogram with bins, box plot, filled and symbol maps, dual-axis combo charts, bullet charts and a Pareto chart, all on the Superstore India data.
   • Choose the right chart for comparison, trend, part-to-whole, distribution, relationship and geography questions
   • Build bar, line, area, pie, donut, treemap and highlight-table views
   • Create bins and histograms, box plots and scatter plots with trend lines
   PDF: download
3. 3. Calculations in Tableau: Calculated Fields, Table Calculations and LOD Expressions Intermediate 150 min
   Write calculated fields (row-level and aggregate), use string, date, number and logical functions, handle nulls, then master table calculations (running total, percent of total, difference and growth, rank, moving average, and Compute Using) and Level of Detail expressions (FIXED, INCLUDE, EXCLUDE), with every result checked against pandas.
   • Write row-level and aggregate calculated fields and know which one a question needs
   • Use IF/ELSEIF, CASE, IIF, ZN, IFNULL, DATEDIFF, DATETRUNC and string functions
   • Apply quick table calculations and control them with Compute Using
   PDF: download
4. 4. Filters, Parameters, Sets, Groups and Hierarchies in Tableau Intermediate 120 min
   Control what a view shows and let users interact with it. Learn every filter type and where it sits in the order of operations, context filters and Top N, groups, hierarchies, bins, sets (fixed, conditional, top) and combined sets, and parameters for dynamic Top N, measure swapping and what-if analysis.
   • Use dimension, measure, date, context, data-source and table-calculation filters correctly
   • Build hierarchies and groups, and explain groups vs sets
   • Create fixed, conditional and Top N sets and use IN/OUT in calculations
   PDF: download
5. 5. Data Modelling in Tableau: Relationships, Joins, Unions, Blending, Extracts and Tableau Prep Intermediate 120 min
   Combine and shape data in Tableau. Understand the logical layer (relationships) and the physical layer (joins), when to union or blend, how row duplication inflates totals, live connections vs extracts, data interpreter and pivoting, and how Tableau Prep Builder cleans data in repeatable flows, using the Adventure Cycles star schema.
   • Build a relationships-based data model and explain why it avoids duplicated totals
   • Choose between relationships, joins, unions and blends
   • Pivot, split and clean data on the Data Source page and in Tableau Prep
   PDF: download
6. 6. Dashboards, Actions, Stories and Publishing in Tableau (Capstone) Intermediate 180 min
   Turn sheets into an interactive dashboard and a data story. Plan the layout with containers, add filter, highlight, URL, parameter and set actions, design for phones, tell a story with Story Points, publish to Tableau Public or Cloud, and complete two capstones, a Superstore India sales dashboard and the video-game regional sales case study from class.
   • Lay out a dashboard with tiled and floating objects, containers and device layouts
   • Add filter, highlight, URL, go-to-sheet, parameter and set actions
   • Build a Story with Story Points that explains an insight step by step
   PDF: download

Generative AI for analysts: prompting, AI vs GenAI vs agentic AI, AI over SQL (Metabase, MinusX), Copilot and Gemini in Excel, and office agents.

1. 1. Generative AI for Analysts: How It Works, Prompting & AI vs GenAI vs Agentic AI Beginner 110 min
   Understand what generative AI is and how large language models behave (tokens, context, temperature, hallucination), how AI, machine learning, deep learning, GenAI and agentic AI differ, and how to write prompts that give analysts accurate, checkable results, with reusable templates and privacy rules.
   • Explain the relationship between AI, ML, deep learning, generative AI and agentic AI
   • Describe in plain language how an LLM generates text and why it can be confidently wrong (hallucination)
   • Write prompts using role, context, task, format and constraints, with examples and step-by-step reasoning
   PDF: download
2. 2. AI with SQL: Text-to-SQL, Docker, Metabase & MinusX Intermediate 130 min
   Use AI to write, explain and debug SQL safely. Learn how text-to-SQL works and where it fails, give the model the right schema, protect your database with read-only access, install Docker, run Metabase on your own data, connect an AI assistant such as MinusX, and validate every generated query.
   • Explain how text-to-SQL works and why context (schema, definitions, examples) decides quality
   • Write a schema-aware prompt and review generated SQL for the usual errors
   • Install Docker and run Metabase locally; connect a database; build questions, models and dashboards
   PDF: download
3. 3. AI in Excel & Office: Copilot, Gemini, Claude, Python in Excel & Agents Intermediate 120 min
   Use AI where analysts work every day. Work with Copilot in Excel (formulas, insights, charts, the COPILOT function), Gemini in Google Sheets and Excel add-ins, Claude and other assistants for formulas and files, Python in Excel, and office agents that perform multi-step tasks, and learn how to prompt, verify and stay safe.
   • Prepare a workbook so AI tools understand it (Tables, clear headers, no merged cells)
   • Use Copilot and Gemini-style assistants to explain, write and debug formulas, create pivots and charts, and summarise data
   • Use the Excel COPILOT function and Python in Excel for text, classification and analysis inside cells
   PDF: download
4. 4. The AI-Assisted Analyst Workflow, Agents & Governance (Capstone) Intermediate 140 min
   Combine everything into one repeatable workflow: frame a question, brief the AI, analyse with code, verify, visualise and write the story. See how an analyst agent works (plan, tools, observe, repeat) with a runnable toy example, learn MCP and tool-calling basics, and finish with governance, ethics and a telecom-churn capstone.
   • Apply a seven-step AI-assisted analysis workflow from question to recommendation
   • Explain the agent loop, tool calling and the Model Context Protocol (MCP) at a conceptual level
   • Build a tiny agent-style loop that plans, runs SQL tools and reports, and describe where an LLM would sit
   PDF: download

Python from zero: data types, control flow, data structures, functions, OOP, files, NumPy, pandas, visualisation, dates, SQL connections, EDA and DSA for data roles.

1. 1. Introduction to Python: Why, Install & Jupyter Notebooks Beginner 90 min
   Learn what programming and Python are, how Python compares with other languages, how code runs (interpreters, compilers, bytecode), the properties of Python, and set up your environment (Anaconda, VS Code, Jupyter, Google Colab). Write and run your first cells, with markdown, magic commands and good notebook habits.
   • Explain what a programming language is and why Python is the default language for data work
   • Describe the difference between compiled and interpreted languages and how Python runs your code
   • Install Python and Jupyter (or use Google Colab) and run code in cells
   PDF: download
2. 2. Variables, Data Types, Type Conversion, print(), f-strings & input() Beginner 110 min
   Store and name values with variables, meet Python's core data types (int, float, str, bool, None, complex), convert between types, format output with print(), f-strings and .format(), and read user input with input() and sys.argv.
   • Create variables and follow Python naming rules and conventions
   • Identify and check types with type() and isinstance(); explain mutable vs immutable
   • Convert between int, float, str and bool, and predict what int(), float(), bool() and str() do
   PDF: download
3. 3. Operators, Strings, Indexing, Slicing & String Methods Beginner 120 min
   Master Python's operators (arithmetic, comparison, logical, assignment, membership, identity, bitwise) and work with text: string indexing and slicing, immutability, every string method an analyst needs (split, join, strip, replace, find, startswith, case methods, isdigit…), escape sequences, and cleaning real messy text.
   • Use arithmetic, comparison, logical, membership and identity operators and explain operator precedence
   • Index and slice strings forwards and backwards, including steps, and explain immutability
   • Apply string methods to clean, split, search, join and format text
   PDF: download
4. 4. Control Flow: if, elif, else, Nested Conditions & match Beginner 90 min
   Make programs decide. Learn indentation, if/elif/else, comparison and logical conditions, truthiness, conditional expressions (ternary), nested decisions, the match statement, and how Python's if maps to Excel's IF/IFS and SQL's CASE WHEN, with data-flavoured examples.
   • Write correct if / elif / else blocks and explain why indentation matters
   • Combine conditions with and, or, not, in, chained comparisons and truthiness
   • Use conditional expressions and the match statement
   PDF: download
5. 5. Loops: while, for, range, break, continue & Patterns Beginner 110 min
   Repeat work without repeating code. Learn while and for loops, range(), enumerate(), zip(), break, continue, the loop else clause, nested loops, accumulation, search and counting patterns, and common loop bugs; with an eye on when to replace loops with vectorised pandas/NumPy.
   • Write while and for loops and choose between them
   • Use range(), enumerate() and zip() for index, value and parallel iteration
   • Control loops with break, continue and the loop-else clause; avoid infinite loops
   PDF: download
6. 6. Lists: Creating, Slicing, Methods, Sorting & Comprehensions Beginner 120 min
   Store and process ordered collections with lists. Index and slice them, add, remove and sort items, understand mutability, aliasing and copying (shallow vs deep), use nested lists, list comprehensions, and common patterns for cleaning and summarising data.
   • Create lists and use indexing, slicing, concatenation, repetition and membership tests
   • Apply list methods (append, extend, insert, remove, pop, sort, reverse, index, count) and built-ins (len, sum, min, max, sorted)
   • Explain mutability, aliasing and the difference between assignment, shallow copy and deep copy
   PDF: download
7. 7. Tuples & Sets: Immutable Records, Unpacking and Set Algebra Beginner 90 min
   Use tuples for fixed records and multiple return values, master unpacking and named tuples, and use sets for uniqueness, fast membership tests and set algebra (union, intersection, difference) on real customer data.
   • Create tuples, explain immutability and hashability, and unpack tuples including starred unpacking
   • Use namedtuple and dataclass-style records for readable fixed structures
   • Create sets and frozensets and use add, discard, remove, update and set operators
   PDF: download
8. 8. Dictionaries: Key-Value Data, Counting and Grouping Beginner 100 min
   Store and look up data by key. Create and update dictionaries, use get, setdefault, items, Counter and defaultdict, nest dictionaries, and convert between dictionaries, JSON-like records and DataFrames using the Superstore data.
   • Create dictionaries and read, add, update and delete keys safely
   • Loop over keys, values and items and merge dictionaries
   • Count and group with get, setdefault, Counter and defaultdict
   PDF: download
9. 9. Functions: Reusable Code, Arguments, Scope and Docstrings Beginner 100 min
   Package logic into reusable functions. Learn def, parameters and arguments (positional, keyword, default, *args, **kwargs), return values, scope, docstrings and type hints, plus testing small functions on real data.
   • Define and call functions with positional, keyword and default arguments
   • Use *args and **kwargs and return multiple values
   • Explain local vs global scope and avoid the mutable-default trap
   PDF: download
10. 10. Comprehensions, Lambda, map/filter and Generators Beginner 100 min
    Write compact, readable Python. Learn list, set and dict comprehensions, lambda with sorted/min/max, map and filter, any and all, generators and itertools, and when plain loops or pandas are the better choice.
    • Write list, set and dictionary comprehensions with conditions and nesting
    • Use lambda functions with sorted, min, max, map and filter
    • Use any, all, zip, enumerate and sum with generator expressions
    PDF: download
11. 11. Object-Oriented Python: Classes, Objects, Inheritance and Dataclasses Intermediate 110 min
    Model real things as objects. Learn classes, __init__, attributes and methods, encapsulation, inheritance, polymorphism, special (dunder) methods, class and static methods, properties and dataclasses, with a small data-pipeline example.
    • Define classes with attributes and methods and create objects
    • Use inheritance, super() and polymorphism to share and customise behaviour
    • Implement __str__, __repr__, __eq__ and __len__ to make objects behave like built-ins
    PDF: download
12. 12. Files, Exceptions, JSON and CSV Intermediate 110 min
    Read and write text, CSV and JSON files safely with pathlib and with-blocks, handle errors with try/except/else/finally, raise your own exceptions, and log what happened, using a small "load a messy file" project.
    • Open, read and write text files with with-blocks and pathlib
    • Read and write CSV with the csv module and JSON with the json module
    • Handle errors with try, except, else and finally, and catch specific exceptions
    PDF: download
13. 13. Modules, Packages, Virtual Environments and Git Intermediate 90 min
    Organise code into modules and packages, install libraries with pip or uv inside virtual environments, pin dependencies, use the standard library, and version-control your projects with Git and GitHub.
    • Import modules in the different ways and explain if __name__ == "__main__
    • Create a package with __init__.py and a sensible project layout
    • Create virtual environments and install and pin packages with pip or uv
    PDF: download
14. 14. Debugging, Testing, Regular Expressions and Code Quality Intermediate 100 min
    Find and fix bugs systematically, write automated tests with pytest, clean text with regular expressions, and keep code readable with PEP 8, type hints, linters and formatters.
    • Read a traceback and debug with print, breakpoints and pdb
    • Write and run unit tests with assert and pytest, including parametrised tests
    • Use regular expressions to search, extract, validate and replace text
    PDF: download
15. 15. NumPy: Fast Arrays, Vectorisation and Broadcasting Intermediate 120 min
    Learn the array library under pandas, scikit-learn and PyTorch. Create arrays, understand shape and dtype, index and slice in 1-D and 2-D, filter with boolean masks, compute with vectorised operations, aggregations along axes and broadcasting, generate random data and do basic linear algebra.
    • Create arrays and describe their shape, ndim, dtype and size
    • Index, slice and filter 1-D and 2-D arrays with boolean masks and fancy indexing
    • Use vectorised arithmetic, universal functions and aggregations along an axis
    PDF: download
16. 16. pandas I: Series, DataFrames, Reading Data, Selecting and Filtering Intermediate 120 min
    Meet the most-used data library. Create Series and DataFrames, read CSV and Excel files, inspect data with head, info and describe, select columns and rows with loc and iloc, filter with conditions and query, sort, add columns and save results, using the Superstore sales data.
    • Create Series and DataFrames and explain the index
    • Read CSV and Excel files with the right options and write results back out
    • Inspect a dataset with shape, dtypes, head, info, describe and value_counts
    PDF: download
17. 17. pandas II: Data Cleaning: Missing Values, Types, Duplicates, Text and Outliers Intermediate 120 min
    Turn messy data into analysis-ready data. Detect and treat missing values, fix data types, remove duplicates, standardise text, parse dates, handle outliers with IQR and caps, and document every step in a reusable cleaning function.
    • Profile a dataset for missing values, wrong types, duplicates and inconsistent categories
    • Choose and apply missing-value strategies (drop, fill with statistic, group-wise fill, flag)
    • Convert types safely with to_numeric, to_datetime and astype, including categories
    PDF: download
18. 18. pandas III: GroupBy, Pivot Tables, Merge/Join and Reshape (melt/unpivot) Intermediate 120 min
    Summarise and combine data. Use groupby with agg, transform and filter, build pivot tables and crosstabs, join tables with merge (inner, left, right, outer, anti), stack with concat, and reshape between wide and long with melt, pivot, stack and unstack.
    • Apply split-apply-combine with groupby, named aggregations and multiple keys
    • Use transform for group-level columns and filter for group-level conditions
    • Build pivot_table and crosstab summaries with totals and percentages
    PDF: download
19. 19. pandas IV: Dates, Time Series, Resampling and Rolling Windows Intermediate 110 min
    Work with time. Parse dates, extract parts with .dt, do date arithmetic, set a DatetimeIndex, resample to weeks, months and quarters, compute rolling and expanding windows, shifts and growth rates, and build a cohort-style monthly report with the daily sales data.
    • Parse and format dates and extract year, month, weekday and quarter
    • Do date arithmetic with Timedelta and DateOffset, including business days
    • Resample time series and use rolling, expanding and exponentially weighted windows
    PDF: download
20. 20. Data Visualisation I: Matplotlib and Choosing the Right Chart Intermediate 110 min
    Pick the right chart for the question and build it with Matplotlib's object-oriented API. Line, bar, histogram, scatter, box and pie charts, subplots, annotations, styling and saving, plus design rules that make charts honest and readable.
    • Choose a chart type from the analytical question (trend, comparison, distribution, relationship, composition)
    • Build charts with fig, ax = plt.subplots() and customise titles, labels, ticks, legends and colours
    • Combine several charts with subplots and annotate key points
    PDF: download
21. 21. Data Visualisation II: Seaborn Statistical Charts and Interactive Plotly Intermediate 100 min
    Make statistical charts quickly with Seaborn (distributions, categorical comparisons, relationships, correlation heatmaps, pair plots and facets) using the HR attrition data, and build interactive charts and simple dashboards with Plotly Express and Streamlit.
    • Use Seaborn's figure-level and axes-level functions with hue, col and row
    • Compare distributions across groups with histplot, kdeplot, boxplot, violinplot and countplot
    • Show relationships with scatterplot, regplot, heatmaps of correlations and pairplot
    PDF: download
22. 22. Exploratory Data Analysis (EDA) Case Study: Telecom Customer Churn Intermediate 150 min
    Run a complete, structured EDA on 3,000 telecom customers. Frame the question, check data quality, do univariate, bivariate and segment analysis, engineer features, quantify revenue at risk and finish with findings and recommendations: the template you will reuse for every dataset and for the ML churn model.
    • Follow a repeatable EDA checklist from question to recommendation
    • Check data quality and consistency between related columns
    • Analyse univariate distributions and bivariate relationships with the target
    PDF: download
23. 23. Python and SQL: sqlite3, DuckDB, SQLAlchemy and pandas.read_sql Intermediate 100 min
    Connect Python to databases. Create and query SQLite with the standard library, use parameterised queries safely, load DataFrames to tables and back, query CSV and DataFrames directly with DuckDB, connect to MySQL, PostgreSQL and SQL Server with SQLAlchemy, and decide what to do in SQL versus pandas.
    • Create a SQLite database, run DDL/DML from Python and fetch results
    • Write parameterised queries and explain SQL injection
    • Move data between pandas and databases with to_sql and read_sql
    PDF: download
24. 24. APIs, JSON and Web Scraping with requests and BeautifulSoup Intermediate 100 min
    Collect data from the web. Understand HTTP, call REST APIs with requests (GET/POST, query parameters, headers, authentication, pagination, retries and rate limits), flatten nested JSON with json_normalize, and scrape HTML tables and pages responsibly with BeautifulSoup and pandas.read_html.
    • Explain HTTP methods, status codes, headers and JSON responses
    • Call REST APIs with parameters, headers and API keys stored safely
    • Handle pagination, timeouts, retries and rate limits
    PDF: download
25. 25. Performance and Bigger Data: Vectorisation, Memory, Parquet, Polars and DuckDB Intermediate 100 min
    Make Python data work fast and scale beyond memory. Measure with timeit, replace loops with vectorised code, shrink DataFrames with the right dtypes, store data as Parquet, use Polars lazy queries and DuckDB for out-of-core analytics, and know when to move to Spark and the cloud.
    • Measure speed and memory before optimising
    • Replace row loops and apply with vectorised pandas and NumPy operations
    • Reduce memory with categories, smaller numeric types and selected columns
    PDF: download
26. 26. DSA I: Big-O, Arrays, Strings, Hashing, Two Pointers and Sliding Window Intermediate 120 min
    Data structures and algorithms for data-analyst, data-scientist and data-engineer interviews. Learn Big-O time and space complexity, then the patterns that solve most array and string questions (hash maps and sets, prefix sums, two pointers, sliding window), with worked interview problems and timings.
    • Estimate time and space complexity with Big-O and compare common growth rates
    • Know the cost of operations on lists, dicts, sets and deques
    • Solve array and string problems with hash maps, counting and prefix sums
    PDF: download
27. 27. DSA II: Stacks, Queues, Linked Lists, Recursion, Sorting and Binary Search Intermediate 120 min
    Learn linear data structures (stack, queue, deque, linked list), recursion and backtracking, the main sorting algorithms with their trade-offs, and binary search including "search on the answer", with interview problems such as valid parentheses, next greater element, reverse a linked list and search in a rotated array.
    • Implement and use stacks, queues and deques, and solve bracket and monotonic-stack problems
    • Build and manipulate a singly linked list (reverse, detect a cycle, find the middle)
    • Write recursive solutions with base cases and use backtracking for combinations
    PDF: download
28. 28. DSA III: Trees, Heaps, Graphs (BFS/DFS) and Dynamic Programming Advanced 130 min
    Finish the DSA toolkit. Binary trees and binary search trees with traversals, heaps and priority queues with heapq (top-k, merge k lists, running median), graphs with adjacency lists, BFS and DFS, shortest paths and topological sort (as used in data pipelines), and dynamic programming from memoisation to tables.
    • Traverse binary trees (pre-, in-, post- and level-order) and use a binary search tree
    • Use heapq for top-k, k-way merge, scheduling and running medians
    • Represent graphs and apply BFS, DFS, Dijkstra and topological sort
    PDF: download
29. 29. Python Capstone: End-to-End Retail Sales Analytics Project Advanced 180 min
    Bring the whole Python track together on the Superstore data. Structure a project, build a validated data pipeline, compute KPIs, growth and Pareto analysis, cohort retention and discount impact, create a chart pack and an Excel report, and write the README and executive summary you can put in your portfolio.
    • Organise an analysis as a reproducible project with functions, checks and outputs
    • Build a load → validate → transform pipeline with assertions
    • Analyse KPIs, growth, Pareto concentration, cohorts and discount effects
    PDF: download

Probability, CLT, hypothesis tests, the ML lifecycle, regression, classification, trees, ensembles, clustering, PCA, time series, NLP, deep learning basics, evaluation, explainability and deployment.

1. 1. Descriptive Statistics: Centre, Spread, Shape and Relationships Beginner 100 min
   Describe data with numbers before modelling it. Types of data and measurement scales, mean, median and mode, range, variance, standard deviation, IQR and coefficient of variation, percentiles and z-scores, skewness and kurtosis, covariance and correlation (Pearson and Spearman), all on the house-price and HR datasets.
   • Classify variables as categorical (nominal, ordinal) or numeric (discrete, continuous; interval, ratio)
   • Compute and interpret mean, median, mode, weighted mean and trimmed mean
   • Compute and interpret range, IQR, variance, standard deviation and coefficient of variation
   PDF: download
2. 2. Probability and Distributions: Rules, Bayes, Binomial, Poisson and Normal Beginner 110 min
   The language of uncertainty. Probability rules, conditional probability and Bayes' theorem (with a fraud-alert example), random variables and expected value, and the distributions analysts use most (Bernoulli, binomial, Poisson, uniform, normal, exponential), with scipy.stats and simulation.
   • Apply the addition, multiplication and complement rules and conditional probability
   • Use Bayes' theorem to update probabilities and explain base-rate effects
   • Compute expected value and variance of a random variable
   PDF: download
3. 3. Sampling, the Central Limit Theorem and Confidence Intervals Intermediate 110 min
   Learn how a sample tells us about a population. Population vs sample, sampling methods and biases, sampling distributions and standard error, the Central Limit Theorem by simulation, confidence intervals for means and proportions (z, t and bootstrap), and how to choose a sample size.
   • Distinguish population and sample, parameter and statistic, and name common sampling methods and biases
   • Explain sampling distributions and standard error
   • Demonstrate the Central Limit Theorem by simulation and state when it applies
   PDF: download
4. 4. Hypothesis Testing I: The Framework, p-values, z-tests and t-tests Intermediate 120 min
   Turn business questions into testable hypotheses. Null and alternative hypotheses, significance level, test statistics, p-values and critical values, one- vs two-tailed tests, Type I and II errors and power, then one-sample, two-sample (Welch) and paired t-tests and z-tests for proportions, on a delivery-time case study.
   • Translate a business question into null and alternative hypotheses
   • Explain significance level, test statistic, p-value and critical value, and decide with both
   • Choose one- or two-tailed tests and describe Type I/II errors and power
   PDF: download
5. 5. Hypothesis Testing II: Chi-Square, ANOVA, Non-Parametric Tests and Correlation Tests Intermediate 110 min
   Test relationships between categories with chi-square tests, compare three or more groups with one-way ANOVA and Tukey post-hoc tests, use non-parametric alternatives (Mann-Whitney, Wilcoxon, Kruskal-Wallis) when assumptions fail, test correlations, and control false discoveries when running many tests.
   • Run chi-square tests of independence and goodness of fit and read expected counts
   • Compare several group means with one-way ANOVA and locate differences with Tukey HSD
   • Choose parametric vs non-parametric tests and run Mann-Whitney, Wilcoxon and Kruskal-Wallis
   PDF: download
6. 6. A/B Testing and Experimentation: Design, Power, Analysis and Pitfalls Intermediate 120 min
   Run product experiments the way data teams at e-commerce and fintech companies do. Choose a metric and guardrails, size the test with power analysis, randomise, analyse conversion and revenue with z-tests, t-tests and bootstrap intervals, check sample-ratio mismatch, avoid peeking and novelty effects, and write the decision memo, using a new-checkout experiment.
   • Design an experiment with a hypothesis, primary metric, guardrail metrics and randomisation unit
   • Compute the required sample size with power analysis and a minimum detectable effect
   • Analyse conversion (two-proportion z-test) and revenue per user (Welch t-test and bootstrap)
   PDF: download
7. 7. Introduction to Machine Learning: Types, Business Framing and the ML Lifecycle Beginner 100 min
   What machine learning is and is not, how it differs from rules and statistics, supervised vs unsupervised vs reinforcement learning, regression vs classification vs clustering, turning a business problem into an ML problem, the end-to-end ML lifecycle (CRISP-DM to MLOps), linear vs non-linear models and link functions, and where GenAI fits.
   • Define machine learning and distinguish it from rule-based systems and classical statistics
   • Classify problems as supervised (regression, classification), unsupervised (clustering, dimensionality reduction) or reinforcement learning
   • Translate a business question into target, features, unit of prediction, metric and decision
   PDF: download
8. 8. The scikit-learn Workflow: Train/Test Split, Baselines, Pipelines and Saving Models Intermediate 110 min
   Learn the standard machine-learning workflow in scikit-learn. The estimator API (fit, predict, transform), splitting data into train, validation and test sets with stratification and time order, baselines, ColumnTransformer and Pipeline to avoid leakage, comparing models, and saving and loading a trained pipeline.
   • Use the fit / predict / predict_proba / transform / score API consistently
   • Split data into train and test (stratified, time-based) and explain why the test set is touched once
   • Build dummy baselines and compare real models against them
   PDF: download
9. 9. Data Preprocessing and Feature Engineering for ML Intermediate 120 min
   Prepare features that models can learn from. Imputation strategies, outlier handling, encoding categorical variables (one-hot, ordinal, target encoding), scaling (standard, min-max, robust), transformations (log, Box-Cox/Yeo-Johnson), binning, interactions and polynomial features, date and text features, and feature selection, all inside leak-free pipelines.
   • Impute missing values with simple, group-aware and model-based strategies and add missing indicators
   • Encode nominal and ordinal categories correctly, including high-cardinality columns
   • Choose a scaler and know which algorithms need scaling
   PDF: download
10. 10. Linear Regression: Fitting, Interpreting, Assumptions and Diagnostics Intermediate 130 min
    Predict a number and explain it. Simple and multiple linear regression with ordinary least squares, interpreting coefficients, dummy variables and log targets, R², adjusted R², RMSE and MAE, the LINE assumptions and residual diagnostics, multicollinearity and VIF, outliers and influence, with statsmodels for inference and scikit-learn for prediction on the house-price data.
    • Fit simple and multiple linear regression with statsmodels and scikit-learn
    • Interpret intercepts, slopes, dummy variables and log-transformed coefficients
    • Evaluate models with R², adjusted R², MAE, RMSE and MAPE on test data
    PDF: download
11. 11. Gradient Descent: How Models Learn (Built from Scratch in NumPy) Intermediate 110 min
    Understand the optimisation engine behind linear regression, logistic regression and neural networks. Cost functions, gradients and the update rule, implementing batch gradient descent for linear regression in NumPy, the learning rate, feature scaling, stochastic and mini-batch variants, convergence checks, and comparison with the closed-form OLS solution and scikit-learn's SGDRegressor.
    • Define a cost function (MSE) and explain what its gradient tells us
    • Implement batch gradient descent for linear regression with NumPy
    • Choose a learning rate and diagnose divergence and slow convergence with cost curves
    PDF: download
12. 12. Overfitting, Polynomial Regression and Regularisation (Ridge, Lasso, Elastic Net) Intermediate 110 min
    See overfitting and underfitting happen, learn the bias-variance trade-off with polynomial regression, and control model complexity with L2 (Ridge), L1 (Lasso) and Elastic Net penalties, including choosing the penalty strength with cross-validation, feature selection with Lasso, and learning curves.
    • Recognise underfitting and overfitting from train vs test errors and plots
    • Explain the bias-variance trade-off and how model complexity affects it
    • Fit polynomial regression and control its degree
    PDF: download
13. 13. Logistic Regression: Probabilities, Odds Ratios and Credit-Risk Scoring Intermediate 120 min
    Classify with probabilities. The sigmoid and log-odds, maximum likelihood and log loss, fitting logistic regression with statsmodels (inference, odds ratios) and scikit-learn (pipelines, regularisation), thresholds and decisions, multiclass logistic regression, and scoring new applicants in the Bank Loans case study.
    • Explain why linear regression fails for binary targets and how the sigmoid fixes it
    • Interpret coefficients as log-odds and odds ratios
    • Fit, evaluate and regularise logistic regression in statsmodels and scikit-learn
    PDF: download
14. 14. Classification Metrics: Confusion Matrix, Precision, Recall, ROC, PR and Business Value Intermediate 110 min
    Measure classifiers properly. The confusion matrix, accuracy and why it misleads, precision, recall, specificity, F1 and F-beta, ROC curves and AUC, precision-recall curves, log loss and calibration, lift and gains charts, choosing thresholds by cost or capacity, and multiclass averaging, using the telecom churn model.
    • Build and read a confusion matrix and compute accuracy, precision, recall, specificity and F1
    • Plot and interpret ROC and precision-recall curves and their AUCs
    • Check probability calibration and log loss
    PDF: download
15. 15. Cross-Validation and Hyperparameter Tuning: K-Fold, GridSearchCV, RandomizedSearchCV and Optuna Intermediate 110 min
    Estimate performance reliably and tune models without fooling yourself. Hold-out vs k-fold, stratified, grouped and time-series cross-validation, cross_validate with several metrics, GridSearchCV and RandomizedSearchCV over pipelines, nested cross-validation, Bayesian optimisation with Optuna, and the common leakage traps.
    • Explain why one train/test split is noisy and how k-fold cross-validation helps
    • Choose stratified, group and time-series splitters for the problem
    • Tune pipeline hyperparameters with GridSearchCV and RandomizedSearchCV and read cv_results_
    PDF: download
16. 16. K-Nearest Neighbours: Classifier and Regressor (Bank Loans Case Study) Intermediate 100 min
    The simplest learning algorithm: predict from the most similar past examples. Distance metrics, choosing k, why scaling is essential, weighted voting, the curse of dimensionality, KNN for classification and regression, tuning with GridSearchCV, and the full Bank Loans case study from the live class with metrics and scoring of new applicants.
    • Explain how KNN classifies and regresses using distances to neighbours
    • Compute Euclidean, Manhattan and Minkowski distances and know why scaling matters
    • Choose k and weighting with cross-validation and explain the bias-variance effect of k
    PDF: download
17. 17. Decision Trees: Splits, Impurity, Pruning and Interpretable Rules Intermediate 110 min
    Learn the model behind random forests and gradient boosting. How trees split data with Gini impurity, entropy and variance reduction, growing and visualising a tree, reading it as business rules, controlling overfitting with depth, minimum leaf size and cost-complexity pruning, regression trees, feature importance and the strengths and weaknesses of single trees.
    • Explain recursive binary splitting and compute Gini impurity and entropy by hand
    • Train, plot and read a decision tree classifier as IF-THEN rules
    • Control overfitting with max_depth, min_samples_leaf and ccp_alpha pruning
    PDF: download
18. 18. Ensembles I: Bagging and Random Forests Intermediate 100 min
    Combine many models to beat one. The wisdom of crowds, bootstrap aggregating (bagging), random forests with feature subsampling, out-of-bag evaluation, the key hyperparameters, feature importance (impurity vs permutation), extra trees, voting and stacking ensembles, applied to telecom churn.
    • Explain why averaging many diverse models reduces variance
    • Build bagging and random-forest models and use out-of-bag scores
    • Tune n_estimators, max_features, max_depth and min_samples_leaf
    PDF: download
19. 19. Ensembles II: Gradient Boosting, XGBoost, LightGBM and CatBoost Advanced 120 min
    The algorithm family that wins most tabular-data problems. Boosting intuition (AdaBoost to gradient boosting), fitting trees to residuals by hand, learning rate and number of trees, early stopping, scikit-learn's HistGradientBoosting, XGBoost and LightGBM APIs and key hyperparameters, categorical features and CatBoost, and a tuned comparison on churn and house prices.
    • Explain sequential boosting and how gradient boosting fits trees to residuals (gradients)
    • Implement a few boosting rounds by hand to see the mechanism
    • Tune learning rate, number of trees, depth, subsampling and regularisation with early stopping
    PDF: download
20. 20. Support Vector Machines and Naive Bayes Intermediate 100 min
    Two classic classifiers with very different ideas. SVMs find the widest margin between classes, use soft margins (C) and kernels (RBF, polynomial) for non-linear boundaries, and need scaling; Naive Bayes applies Bayes' theorem with an independence assumption and is a fast, strong baseline for text. Includes SVR, probability calibration and when to choose each.
    • Explain maximum-margin classification, support vectors and the role of C
    • Use linear and RBF kernels and tune C and gamma
    • Apply SVR for regression and know SVM scaling and size limits
    PDF: download
21. 21. Imbalanced Classification: Fraud Detection with Class Weights, Resampling and Thresholds Advanced 110 min
    Most valuable classification problems are rare-event problems (fraud, defaults, churn, failures). Learn why accuracy and naive training fail, the right metrics (PR-AUC, recall at fixed precision, cost), class weights, undersampling, oversampling and SMOTE inside pipelines, threshold moving, and anomaly-detection alternatives, on a synthetic card-fraud dataset with about 1.4% fraud.
    • Recognise imbalanced problems and the metrics that work for them
    • Apply class_weight and scale_pos_weight to make models pay attention to the rare class
    • Use random undersampling, oversampling and SMOTE correctly inside cross-validation
    PDF: download
22. 22. Clustering I: K-Means and RFM Customer Segmentation Intermediate 120 min
    Find groups without labels. Heuristic RFM segmentation (recency, frequency, monetary scores and named segments) as taught in class, then K-means clustering, scaling and log transforms, choosing k with the elbow method and silhouette score, profiling and naming clusters, and turning segments into marketing actions, on 4,500 retail transactions.
    • Compute recency, frequency and monetary value per customer from transactions
    • Build heuristic RFM scores and named segments (Champions, At risk, Hibernating…)
    • Run K-means, explain its algorithm and its assumptions, and scale features properly
    PDF: download
23. 23. Clustering II and Dimensionality Reduction: Hierarchical, DBSCAN, Gaussian Mixtures, PCA, t-SNE and UMAP Advanced 120 min
    Go beyond K-means. Agglomerative hierarchical clustering with dendrograms and linkage choices, density-based DBSCAN for irregular shapes and outliers, Gaussian mixture models with soft assignments, and dimensionality reduction with PCA (explained variance, loadings, compression), plus t-SNE and UMAP for visualisation, applied to video-game sales and HR data.
    • Build and read a dendrogram and choose a linkage method
    • Use DBSCAN to find irregular clusters and noise points, and tune eps and min_samples
    • Fit Gaussian mixture models and use soft cluster probabilities and BIC
    PDF: download
24. 24. Time-Series Forecasting: Decomposition, Baselines, ETS, ARIMA and ML with Lag Features Advanced 130 min
    Forecast demand properly. Components of a time series (trend, seasonality, noise), decomposition with STL, stationarity and autocorrelation (ADF, ACF/PACF), honest baselines (naive, seasonal naive, moving average), exponential smoothing (Holt-Winters), SARIMA, machine learning with lag and calendar features, backtesting with forecast metrics (MAE, RMSE, MAPE, WAPE), prediction intervals, and a guide to Prophet, statsforecast and foundation models.
    • Decompose a series into trend, seasonality and remainder and test stationarity
    • Read ACF and PACF plots and difference a series
    • Build and evaluate naive, seasonal naive, Holt-Winters and SARIMA forecasts
    PDF: download
25. 25. NLP and Text Analytics: Cleaning, TF-IDF, Sentiment Classification, Topics and Embeddings Advanced 130 min
    Turn customer reviews into insight. Text cleaning and tokenisation, stop words, stemming and lemmatisation, bag-of-words and TF-IDF with n-grams, a sentiment classifier with error analysis, aspect-level insight, topic modelling with NMF, document similarity, and how embeddings and LLMs change NLP, on 3,000 e-commerce reviews.
    • Clean and tokenise text and decide when to remove stop words, stem or lemmatise
    • Represent documents with bag-of-words and TF-IDF (with n-grams) and read the vocabulary
    • Train, evaluate and interpret a sentiment classifier, including error analysis
    PDF: download
26. 26. Neural Networks and Deep Learning: From a Neuron to Transformers Advanced 130 min
    Understand the models behind modern AI. Neurons, weights and activation functions, forward pass and backpropagation, a two-layer network written from scratch in NumPy, multilayer perceptrons in scikit-learn on images and tabular data, training practice (learning rate, batches, epochs, early stopping, dropout), and a map of CNNs, RNNs, transformers and LLMs with PyTorch and Keras code.
    • Explain a neuron, layers, activation functions and the forward pass
    • Explain loss, gradients and backpropagation, and train a small network from scratch
    • Train and tune MLPs with scikit-learn and compare them with classical models
    PDF: download
27. 27. Explainable AI and MLOps: SHAP, Fairness, Deployment, Monitoring and Responsible ML Advanced 130 min
    Make models trustworthy and useful in production. Global and local explanations (permutation importance, partial dependence, SHAP), fairness checks across groups, packaging a pipeline, serving predictions with FastAPI, batch scoring, experiment tracking with MLflow, monitoring data drift and performance, model cards, and the regulations and responsible-AI practices that apply in India and globally.
    • Explain a model globally with permutation importance and partial dependence
    • Explain individual predictions with SHAP values and communicate them
    • Check performance and error rates across groups for fairness
    PDF: download
28. 28. ML Capstone: End-to-End Churn Prediction and Retention Strategy Advanced 180 min
    Put the whole ML track together. Frame the churn problem, build leak-free features, compare baselines and models with cross-validation, tune the winner, choose a profit-maximising threshold under a budget, explain predictions, design segment-level retention actions with an A/B test, and write the model card, deployment plan and executive summary for your portfolio.
    • Frame a churn problem with a decision, metric, baseline and constraints
    • Build a reproducible pipeline with engineered features and compare models with cross-validation
    • Tune and evaluate the final model on an untouched test set
    PDF: download

How LLMs work, prompting, LLM APIs in Python, embeddings and vector search, RAG, tool use, agents, MCP, evaluation, guardrails, fine-tuning and responsible AI.

1. 1. How Large Language Models Work: Tokens, Embeddings, Transformers and Training Beginner 100 min
   Open the black box. Tokens and tokenisation (built from scratch), next-token prediction and sampling with temperature, embeddings, attention and the transformer, pre-training, instruction tuning and RLHF, context windows, reasoning models, why LLMs hallucinate, and how to choose among Claude, GPT, Gemini, Llama, Mistral, DeepSeek and Qwen.
   • Explain tokens, vocabularies and why token counts drive cost and limits
   • Describe next-token prediction and the effect of temperature and top-p sampling
   • Explain embeddings, self-attention and the transformer at an intuitive level
   PDF: download
2. 2. Prompt Engineering in Depth: Patterns, Templates, Few-Shot, Reasoning and Structured Output Beginner 110 min
   Write prompts that work reliably in products, not just in chat. The anatomy of a production prompt (role, context, task, constraints, format, examples), XML tags and delimiters, few-shot examples chosen by similarity, step-by-step reasoning and extended thinking, structured JSON output with validation, prompt templates and versioning, prompt chaining, and a simple evaluation loop.
   • Structure a prompt with role, context, task, constraints, output format and examples
   • Use delimiters/XML tags to separate instructions from data and resist prompt injection
   • Select few-shot examples and decide when reasoning or extended thinking helps
   PDF: download
3. 3. Calling LLM APIs from Python: Messages, Streaming, Structured Output, Costs and Reliability Intermediate 120 min
   Move from the chat window to code. Set up API keys safely, send messages with system prompts, hold multi-turn conversations, stream responses, get schema-valid JSON, control reasoning effort, cache long prompts, count tokens and estimate cost, batch large jobs, handle errors and retries, and run the same pattern with other providers, with a runnable offline simulator for practice.
   • Store API keys safely and create a client
   • Send single and multi-turn requests with system prompts and read the response blocks
   • Stream output and request structured, validated JSON
   PDF: download
4. 4. Embeddings and Vector Search: Meaning as Numbers, Similarity and Vector Databases Intermediate 110 min
   Learn the foundation of semantic search and RAG. What embeddings are, how word and sentence embeddings are learned (trained here from scratch on our reviews), cosine similarity, document embeddings, building a vector index, exact vs approximate nearest-neighbour search (IVF, HNSW), evaluating retrieval with recall@k, hybrid keyword + vector search, and choosing embedding models and vector databases.
   • Explain embeddings and why similar meanings produce nearby vectors
   • Learn word embeddings from co-occurrence and build document embeddings
   • Use cosine similarity and build exact and approximate vector indexes
   PDF: download
5. 5. Retrieval-Augmented Generation (RAG): Build, Evaluate and Improve a Q&A Assistant Intermediate 140 min
   Ground an LLM in your own documents. RAG architecture, document loading and chunking, indexing, hybrid retrieval and re-ranking, prompt assembly with citations, answer generation (offline simulator plus real Claude code with the citations feature), evaluation of retrieval and answers, failure modes and advanced patterns (query rewriting, contextual retrieval, metadata filters, agentic and graph RAG), built end to end on a retailer's policy handbook.
   • Explain why and when RAG beats fine-tuning or long prompts
   • Chunk documents with metadata and build a searchable index
   • Retrieve with hybrid search, re-rank, and assemble a grounded prompt with citations
   PDF: download
6. 6. Tool Use and Function Calling: Letting LLMs Query Data, Call APIs and Take Actions Intermediate 120 min
   Connect a model to the outside world. How function calling works (tool definitions, JSON schemas, tool_use and tool_result blocks), the request–execute–respond loop, writing good tool descriptions, strict schemas and validation, parallel calls, error handling, server-side tools (web search, code execution), and safety controls, with a runnable sales-analytics assistant that answers questions by calling SQL and calculator tools.
   • Define tools with names, descriptions and JSON input schemas
   • Implement the tool-use loop and return tool results (including errors) correctly
   • Use the SDK tool runner, strict schemas and parallel tool calls
   PDF: download
7. 7. AI Agents and Agentic AI: Loops, Planning, Memory, Multi-Agent Systems and When to Use Them Intermediate 120 min
   Understand what makes software "agentic". Workflows vs agents, the agent loop (observe, think, act), ReAct-style reasoning with tools, planning and task decomposition, short- and long-term memory, guardrails and stopping conditions, multi-agent patterns (orchestrator–workers, evaluator–optimiser, routing), the 2026 agent platforms, and how to decide whether a problem needs an agent at all, with a runnable data-analysis agent.
   • Distinguish single LLM calls, workflows and autonomous agents
   • Implement an agent loop with tools, an observation history and stopping conditions
   • Apply planning, reflection and memory patterns
   PDF: download
8. 8. Model Context Protocol (MCP): Connecting AI Assistants to Your Data and Tools Intermediate 100 min
   Learn the open standard that lets any AI application use any tool or data source. MCP architecture (hosts, clients, servers), the three primitives (tools, resources, prompts), transports (stdio and Streamable HTTP), building and testing a real MCP server for sales data in Python, connecting it to Claude Desktop, Claude Code and other clients, using remote MCP servers from the API, and securing MCP deployments.
   • Explain the problem MCP solves and its host–client–server architecture
   • Distinguish tools, resources and prompts and choose the right primitive
   • Build an MCP server in Python and test it in-process
   PDF: download
9. 9. Evaluating LLM Applications and Building Guardrails: Test Sets, LLM-as-Judge, Injection, PII and Safety Intermediate 120 min
   Ship GenAI features you can trust. Build evaluation sets, choose metrics (exact match, rubric scores, groundedness), calibrate LLM-as-judge against humans, run regression tests on every prompt change, and protect applications with input and output guardrails: prompt-injection defences, PII detection and redaction (Indian identifiers), schema validation, refusal handling, red-teaming and production monitoring.
   • Build an evaluation set and pick metrics for classification, extraction, RAG and generation tasks
   • Use LLM-as-judge with rubrics and measure its agreement with human labels
   • Run regression evaluations when prompts or models change
   PDF: download
10. 10. Customising Models: Prompting vs RAG vs Fine-Tuning, LoRA, Distillation and Open-Weight Models Advanced 100 min
    Decide how to adapt a model to your task. The customisation ladder (prompting, few-shot, RAG, tools, fine-tuning, training), what fine-tuning is good and bad at, preparing training data, parameter-efficient fine-tuning with LoRA and QLoRA (with the maths), distillation from a large to a small model, running open-weight models locally with Ollama and at scale with vLLM, and the cost, privacy and quality trade-offs of API vs self-hosting.
    • Choose between prompting, RAG, tools and fine-tuning for a requirement
    • Prepare a fine-tuning dataset in chat format and split it for evaluation
    • Explain LoRA/QLoRA and compute their parameter savings
    PDF: download
11. 11. GenAI for Data Work: Text-to-SQL, AI Coding Assistants, Data Cleaning and Automated Insights Intermediate 120 min
    Apply LLMs to everyday analytics and engineering. Schema-aware text-to-SQL with guardrails and execution-accuracy evaluation, AI coding assistants and agents in notebooks and IDEs, LLM-assisted data cleaning (normalising messy categories, extracting fields from text), generating narrative insights from tables safely, and a workflow that keeps the analyst in control.
    • Build a schema-aware text-to-SQL prompt with read-only execution and validation
    • Evaluate text-to-SQL with execution accuracy on a gold question set
    • Use AI coding assistants effectively and safely for analysis code
    PDF: download
12. 12. Building and Shipping a GenAI App: Architecture, Streamlit/FastAPI, Cost, Observability and Responsible AI (Capstone) Intermediate 150 min
    Put the GenAI track together. Reference architecture for an LLM application, a support-assistant capstone (RAG + tools + guardrails + evaluation), a Streamlit chat front end and a FastAPI back end, session memory, streaming, cost and latency budgets, caching, observability and tracing, deployment options, a launch checklist and responsible-AI governance, with a runnable cost and capacity planner.
    • Design the architecture of a production LLM application
    • Build a chat UI and an API around an LLM pipeline
    • Plan cost, latency and capacity with caching and model routing
    PDF: download

No-code track for PMs, BAs and senior PMs: APIs, MCP with Claude, how AI agents work and how to build them, connecting apps with n8n, Make, Zapier and Replit, a complete Claude Code tutorial, and voice agents and voice cloning.

1. 1. APIs Without Code: How Apps Talk, REST, JSON, Authentication, Webhooks and Postman for PMs and BAs Beginner 120 min
   Understand APIs well enough to write requirements, read documentation, test endpoints and design integrations without writing code. Learn requests and responses, REST verbs and status codes, JSON, authentication (API keys, OAuth 2.0), rate limits and pagination, webhooks vs polling, and how to try any API in Postman, then turn it into a PRD-ready integration spec.
   • Explain what an API, an endpoint, a request and a response are, with real examples
   • Read API documentation and JSON, and know what each HTTP method and status code means
   • Choose between API keys and OAuth, and between webhooks and polling
   PDF: download
2. 2. MCP (Model Context Protocol) Without Code: Connect Claude to Your Apps and Data Beginner to Intermediate 120 min
   Learn what the Model Context Protocol is and why it became the standard way to connect AI assistants to tools and data. Understand hosts, clients, servers, tools, resources and prompts; use ready-made connectors in Claude (Google Drive, Gmail, Slack, GitHub, Notion, Jira); add local and remote MCP servers; expose your own workflows as MCP tools with n8n or Zapier without code; and manage security and permissions.
   • Explain MCP and the host/client/server architecture in plain language
   • Distinguish tools, resources and prompts, and what each lets an AI do
   • Enable Claude connectors and add a custom remote MCP server
   PDF: download
3. 3. How AI Agents Work and How to Build One Without Code Intermediate 150 min
   Understand the agent loop (perceive, reason, act, observe), the building blocks of an agent (model, instructions, tools, memory, knowledge, guardrails), the main design patterns, and when not to use an agent. Then build agents without code in Claude (Projects, Skills, connectors), n8n, Make, Zapier Agents and Replit Agent, and evaluate them like a product.
   • Explain the agent loop and the components of an AI agent
   • Choose between a workflow, a single agent and a multi-agent system
   • Build a no-code agent in Claude, n8n or Zapier with tools, memory and guardrails
   PDF: download
4. 4. Connect All Your Apps with Claude, n8n, Make, Zapier and Replit Intermediate 150 min
   Design integrations across your tools with Claude as the brain and n8n, Make, Zapier or Replit as the hands. Learn the four integration patterns, how to pick a platform, how Claude helps you design and debug automations, and build three end-to-end projects - a lead pipeline, a feedback-to-roadmap loop and a weekly executive report - with costs, reliability and security in mind.
   • Choose the right integration pattern and platform for a business need
   • Use Claude to design, generate and debug automations
   • Connect Claude to n8n, Make and Zapier through the API, MCP and webhooks
   PDF: download
5. 5. Claude Code Complete Tutorial: From First Prompt to Agents, MCP, Hooks and Automation Beginner to Advanced 180 min
   Learn Claude Code, Anthropic's agentic coding tool, from installation to advanced workflows. Work in the terminal, IDE, desktop and web; give context with CLAUDE.md; use plan mode, permissions and checkpoints; run slash commands, custom commands and Skills; add MCP servers; automate with hooks, subagents, headless mode and GitHub Actions; and follow best practices that work for PMs, analysts and engineers.
   • Install Claude Code and complete a task end to end in a real project
   • Give Claude the right context with CLAUDE.md, files and plan mode
   • Control safety with permissions, checkpoints and reviews
   PDF: download
6. 6. Voice Agents and Voice Cloning: Tools, Architecture, Build Steps and Responsible Use Intermediate 120 min
   Learn how AI voice agents work (speech-to-text, LLM, text-to-speech, turn-taking, telephony), compare the main platforms (ElevenLabs, Vapi, Retell AI, Bland AI, Synthflow, OpenAI Realtime, Twilio), build a no-code appointment-booking voice agent connected to your calendar and CRM, clone a voice with consent, and design for latency, Indian languages, compliance and quality.
   • Explain the voice-agent pipeline and why latency matters
   • Compare voice-agent and voice-cloning tools and choose one for a use case
   • Build a no-code voice agent with tools, a knowledge base and call transfer
   PDF: download

Complete tutorials for the design and automation tools used across the programs: Figma (design systems, prototypes, Dev Mode, Figma Make) and n8n (workflows, APIs, AI agents, MCP).

1. 1. Figma Complete Tutorial: Interface, Auto Layout, Components, Variables, Prototypes, Dev Mode and Figma AI Beginner to Advanced 180 min
   Learn Figma from zero to a handoff-ready design. Tour the interface, master frames, shapes, text and the 8-point grid, build responsive layouts with auto layout and constraints, create components with variants and properties, use styles and variables (light and dark modes), prototype flows with Smart Animate and overlays, hand off in Dev Mode, run workshops in FigJam, and generate working prototypes with Figma AI and Figma Make. Includes a dashboard-design project for data roles.
   • Navigate Figma Design and know when to use Figma Design, FigJam, Dev Mode, Slides, Sites and Make
   • Build screens with frames, auto layout, constraints and an 8-point spacing system
   • Create reusable components with variants, component properties and a small design system using variables
   PDF: download
2. 2. n8n Complete Tutorial: Workflow Automation, Data Pipelines and AI Agents Beginner to Advanced 180 min
   Learn n8n, the open, self-hostable workflow-automation tool. Set it up on n8n Cloud or Docker, understand triggers, nodes, credentials, items and expressions, transform data with Edit Fields, IF, Switch, Merge, Loop and Code nodes, call any API with HTTP Request, handle errors and schedules, build AI agents with chat models, memory, tools and vector stores, and connect n8n to MCP. Four complete projects: lead capture, a daily sales report, an email-triage AI agent and a document Q&A bot.
   • Install or sign up for n8n and build, test and activate a workflow
   • Explain triggers, nodes, items and expressions, and transform data between apps
   • Call REST APIs with HTTP Request and write JavaScript or Python in the Code node
   PDF: download

End-to-end capstone, portfolio and GitHub, analyst and data scientist interview preparation with model answers, and a 90-day plan.

1. 1. Portfolio, GitHub and Resume for Data Roles Beginner 90 min
   Turn your learning into evidence employers trust. Choose three to five portfolio projects, structure them on GitHub with strong READMEs, publish dashboards and apps, write an ATS-friendly one-page resume with quantified bullets, and optimise LinkedIn and Naukri profiles for analyst, data scientist, data engineer and GenAI roles.
   • Select portfolio projects that match the target role
   • Publish projects on GitHub with professional READMEs and live demos
   • Write a one-page, ATS-friendly resume with quantified impact bullets
   PDF: download
2. 2. Data Analyst Interview Preparation: SQL, Excel, Power BI, Statistics and Case Questions Intermediate 120 min
   Prepare for analyst interviews with the question types that appear most often, model answers and practice links: SQL coding rounds (joins, aggregation, window functions), Excel and Power BI questions, statistics and A/B testing, metric and product-sense cases, and behavioural questions with the STAR method.
   • Solve common SQL interview patterns quickly and explain your approach
   • Answer core Excel, Power BI and DAX questions
   • Explain key statistics and A/B testing concepts clearly
   PDF: download
3. 3. Data Scientist, ML and GenAI Interview Preparation: Questions and Model Answers Advanced 120 min
   A compact question bank with model answers for data scientist, ML engineer and GenAI roles: Python and pandas, statistics, ML fundamentals, model evaluation, feature engineering, system and case design (churn, fraud, recommendations), MLOps, LLMs, RAG and agents, plus how to handle take-home assignments and live coding.
   • Answer core Python, statistics and ML questions concisely
   • Walk through an end-to-end ML system design
   • Explain LLM, RAG and agent concepts and trade-offs
   PDF: download
4. 4. Your 90-Day Plan: Learning Roadmap, Job Search Strategy and Growing in Your First Role Beginner 60 min
   Turn this handbook into a job. A week-by-week 90-day study and project plan for analyst, data science and GenAI tracks, a weekly routine, a job-search funnel with referrals and outreach messages, salary research and negotiation basics, and habits that help you grow in the first 6 months on the job.
   • Follow a realistic 90-day roadmap with weekly goals
   • Run a job-search funnel with referrals and targeted applications
   • Prepare for salary discussions with market data
   PDF: download

Complete SFMC guide: data extensions, SQL, AMPscript, Email Studio, Automation Studio, Journey Builder, mobile channels, deliverability, Einstein and certification.

1. 1. Salesforce Marketing Cloud (SFMC) Complete Guide: Email Studio, Data Extensions, SQL, AMPscript, Journey Builder and Certification Beginner to Advanced 240 min
   A complete training guide to Salesforce Marketing Cloud Engagement for marketers, analysts and developers. Learn the architecture and studios, subscribers and data extensions, data modelling and Contact Builder, SQL Query Activities, segmentation, Content Builder and AMPscript personalisation, Email Studio sends, Automation Studio, Journey Builder, Mobile Studio (SMS, push, WhatsApp), deliverability, consent and the DPDP Act, reporting, Einstein AI, Data Cloud and Agentforce, plus a capstone and the Marketing Cloud Email Specialist and Administrator certification paths.
   • Explain the Marketing Cloud architecture, studios and builders and when to use each
   • Model data with data extensions, sendable and testable data, primary keys and Contact Builder
   • Segment audiences with filters and SQL Query Activities, and personalise content with AMPscript
   PDF: download

Complete digital marketing guide: strategy, SEO and AI search, Google and Meta Ads, social and influencers, email and WhatsApp, GA4 and attribution, CRO, budgets and AI.

1. 1. Digital Marketing Complete Guide: Strategy, SEO, Google and Meta Ads, Social, Email, WhatsApp, Analytics and AI Beginner to Advanced 240 min
   A complete digital marketing guide for India. Build a strategy and funnel, research customers and keywords, do on-page, technical and local SEO plus AI search (AEO/GEO), run Google Ads and Meta Ads with the right bidding, targeting and creatives, grow social and influencer programmes, run email and WhatsApp marketing, measure with GA4, UTMs and attribution, optimise conversion rates, plan budgets with unit economics, and use AI tools responsibly, with a full campaign capstone.
   • Build a marketing strategy with positioning, personas, funnel stages and KPIs
   • Plan and execute SEO including technical, local and AI-search optimisation
   • Set up and optimise Google Ads and Meta Ads campaigns
   PDF: download

Complete content creation guide: niche and pillars, hooks and writing, short and long video, design, AI tools, publishing system, growth, analytics and monetisation.

1. 1. Content Creation Complete Guide: Strategy, Writing, Short and Long Video, Design, AI Tools, Distribution and Monetisation Beginner to Advanced 210 min
   A complete guide for creators, marketers and professionals building a personal or brand presence. Find your niche and content pillars, write hooks, scripts, LinkedIn posts, threads and blogs, shoot and edit short and long video, design thumbnails and carousels, use AI tools responsibly, publish on a system, grow on Instagram, YouTube and LinkedIn, measure what works, and monetise through brand deals, products, courses and services.
   • Define a niche, audience and content pillars, and plan a sustainable calendar
   • Write hooks, scripts, posts and long-form articles that people finish
   • Produce short and long videos, thumbnails and carousels with free tools
   PDF: download

Complete FDE guide: the role, skills stack, deployment lifecycle, LLM solutions for customers, integration patterns, a capstone and interview preparation.

1. 1. Forward Deployed Engineer (FDE) Complete Guide: The Role, Skills, AI Deployments, Integrations and Interviews Intermediate to Advanced 210 min
   Understand the Forward Deployed Engineer role made famous by Palantir and now central at AI companies such as OpenAI and Anthropic and at enterprise software firms. Learn what FDEs do, the skills stack (software engineering, data, AI/LLM systems, integrations, cloud, security, customer skills), the deployment lifecycle from discovery to production, how to build and evaluate LLM solutions for customers, integration patterns, a capstone deployment and how to prepare for FDE interviews.
   • Explain the FDE role and how it differs from software engineer, solutions engineer and consultant
   • Map the skills stack and build a learning plan for it
   • Run a customer deployment from discovery to production with clear success metrics
   PDF: download

Complete public speaking guide: confidence, structure (PREP, STAR, pyramid), storytelling, data and slides, voice and body language, Q&A, meetings, interviews, video and AI practice tools.

1. 1. Public Speaking Complete Guide: Confidence, Structure, Storytelling, Delivery, Slides, Meetings, Interviews and Video Beginner to Advanced 180 min
   A practical guide to speaking with confidence at work and on stage. Manage nerves, structure any talk with proven frameworks, tell stories with data, design clear slides, master voice, pace and body language, handle Q&A and tough questions, speak in meetings, interviews and stand-ups, present on video and in hybrid rooms, and practise with AI tools, with a 30-day plan and a capstone talk.
   • Manage speaking anxiety with preparation, breathing and reframing techniques
   • Structure talks and answers with frameworks such as PREP, STAR, What-So What-Now What and the pyramid principle
   • Tell stories and present data so audiences remember and act
   PDF: download

An AI engineer builds, ships and runs AI-powered software: calling and customising models, connecting them to data and tools, testing quality, deploying reliably, keeping cost, safety and security under control, and improving the system with real usage.

1. basic The AI engineer role and the lifecycle: Know what the job is, how it differs from neighbouring roles, and the lifecycle you'll work in.
2. basic Foundations: Python, software engineering, Git, APIs, Linux: Build the engineering base that every AI system sits on.
3. basic Math, statistics and machine-learning essentials: Know enough ML to choose methods, read metrics and debug models.
4. intermediate LLM engineering: model APIs, prompts, structured output, cost and latency: Build reliable features on top of model APIs.
5. intermediate RAG, embeddings and vector databases: Build search and question-answering over private data, and measure it.
6. intermediate Agents, tool use and MCP: Build agents that call tools, with control and observability.
7. advanced Customising models: fine-tuning, distillation and open-source models: Decide when to fine-tune, and how, and when not to.
8. advanced Evals, observability, guardrails and red-teaming: Make quality measurable and keep it that way.
9. advanced Deployment and LLMOps: APIs, containers, cloud, CI/CD, scaling and cost: Ship AI services that are reliable, fast and affordable.
10. advanced Data engineering for AI, security and governance: Feed AI systems good data and keep them safe and compliant.
11. advanced System design for AI products and working with the team: Design end-to-end AI systems and collaborate across roles.
12. advanced Career: roadmap, portfolio projects, interviews and job descriptions: Plan 12 months, build proof, and prepare for hiring loops.

AI builder tools let PMs and non-coders research, write, prototype, build websites and apps, and connect tools together. This course shows what each tool is best at and walks you through real builds step by step.

1. basic Choosing the right AI tool: Know the four kinds of AI tools and when to use each.
2. basic Claude for PMs: what you can do and how: Use Claude's Projects, Artifacts, research, connectors and Skills in daily PM work.
3. basic ChatGPT for PMs: Projects, GPTs, Canvas, research and agent: Use ChatGPT's main features for research, documents, data and automation.
4. basic Gemini for PMs: Gemini app, Gems, Deep Research, NotebookLM, Workspace, AI Studio: Use Google's AI tools, especially if your team lives in Google Workspace.
5. intermediate Lovable: from idea to a working app (no code): Build and publish an app with Lovable, including a database, login and your own domain.
6. intermediate Claude Code and OpenAI Codex: coding agents for PMs: Use coding agents to build and change real websites and apps, safely.
7. intermediate Tutorial: create a website, add pages and publish on your domain: Follow one complete path from idea to a live site you own.
8. intermediate Connect your tools: Zapier, Make, n8n, webhooks and MCP: Make your website and tools talk to each other.
9. advanced Connect other websites and services: Embed, integrate and call other websites safely.
10. advanced PM workflows end to end and capstone: Combine tools into a real product workflow.

Webhooks tell your system the moment something happens; triggers decide when automations run; browser automation does the clicking when there's no API; and the Playwright MCP lets an AI assistant like Claude use a real browser for you. Together they're the most-used web automation stack in 2026.

1. basic The web-automation stack: APIs, webhooks, triggers, browsers: See how the pieces fit, and pick the right one for each job.
2. basic Webhooks explained (with real examples): Understand webhooks and receive your first one.
3. intermediate Building reliable webhook receivers: Verify, process and retry webhooks safely in production.
4. basic Triggers: schedules, events, polling and manual: Choose how and when automations start.
5. intermediate Playwright for browser automation: Automate any website reliably with Playwright.
6. intermediate Playwright MCP: let Claude and other AI assistants use a browser: Install and use the Playwright MCP server with Claude Code, Claude Desktop, Cursor and VS Code.
7. intermediate Other browser-automation frameworks and MCPs: Know the alternatives and when each wins.
8. advanced AI browser agents and cloud browsers: Use AI-native automation tools and hosted browsers at scale.
9. advanced Workflow platforms: n8n, Zapier, Make, Pipedream, RPA and scrapers: Run webhooks, triggers and browser steps as complete workflows.
10. advanced Production: security, legality, monitoring, evals and capstone: Run web automations safely and prove they work.

Prompt engineering is how you ask; context engineering is what the AI gets to see when it answers: your instructions, examples, documents, data, memory and tools. Getting both right is the first and most useful AI skill.

1. basic From prompts to context: See why the information you give the AI matters more than clever wording.
2. basic Prompt patterns that work: Use proven patterns: examples, step-by-step, roles, critique and iteration.
3. intermediate Structured outputs: JSON, tables and fixed sections: Get predictable output other tools and people can use directly.
4. intermediate Task decomposition and chaining: Break big jobs into steps the AI can do reliably.
5. intermediate Long context: compression, summaries and memory: Keep long projects accurate when chats and documents get large.
6. intermediate Documents, PDFs, scans and OCR: Get reliable information out of PDFs, slides, spreadsheets and images.
7. advanced Source attribution, fact-checking and knowledge graphs: Make AI outputs traceable to evidence and organise knowledge by relationships.
8. advanced Context engineering for products and agents: Design what your AI feature or agent sees, and test it.

A skill is a reusable method you teach an AI once (instructions, templates, examples, scripts) so it does a recurring task the same good way every time. A tool gives the AI access or actions; memory and evals are parts of the system around it.

1. basic Skills, tools, memory and evals: the system: Know the parts of an AI assistant and where a skill fits.
2. basic Templates: the foundation of every skill: Design templates that make outputs consistent and complete.
3. intermediate Where to build skills: Projects, GPTs, Gems and Agent Skills: Choose the right place to package a skill.
4. intermediate Writing great skill instructions: Write instructions that produce consistent, high-quality results.
5. intermediate A PM skill library: Build a set of skills that covers your core PM work.
6. advanced Connecting skills to sources and tools: Ground skills in your documents and let them act through tools.
7. advanced Testing skills with evals: Prove a skill works and stays working.
8. advanced Project: case study → PRD → presentation skill: Build a portfolio-ready reusable skill end to end (e.g. for a VitaFit-style assignment).

A second brain is a personal knowledge system outside your head: notes, documents, meetings and ideas stored in one trusted place. With AI, it becomes something you can talk to: ask questions across everything you've saved and get answers with sources.

1. basic What a second brain is, and why AI changes it: Understand the idea, the PARA and CODE methods, and what AI adds.
2. basic Capture: getting things into the system: Set up fast, low-friction capture from phone, browser, reading and voice.
3. basic Organise and distil: Turn a pile of captures into findable, useful notes.
4. intermediate Ask AI across your notes: Use NotebookLM, Claude and ChatGPT Projects, Notion AI and Obsidian plugins to question your knowledge.
5. intermediate Context engineering and AI memory: Give AI the right context about you and your work, and manage what it remembers.
6. intermediate Pipelines: meetings, email, reading and learning: Automatically feed your second brain from meetings, email and courses.
7. advanced Second brains for PMs, students and teams: Apply the system to product work, exam prep and team knowledge.
8. advanced Build your own: MCP, automation and evaluation: Connect AI assistants to your notes with MCP and automation, and make sure answers stay accurate.

An eval is a repeatable test that measures how well an AI feature does its job on a fixed set of examples, with a clear way to score each answer. It's the quality bar, the launch gate and the product spec for AI.

1. basic What an eval is, and why PMs own it: Understand evals as the unit test, the quality bar and the product spec for AI features.
2. basic Defining success: criteria, rubrics and failure modes: Turn a fuzzy goal ('helpful answers') into criteria anyone can score the same way.
3. basic Building the eval dataset (golden set): Create a test set that represents real users, including the hard and risky cases.
4. intermediate Grading methods: code, humans and LLM-as-judge: Choose the cheapest grader that measures what matters, and know when to use humans.
5. intermediate Error analysis: finding what actually breaks: Read outputs systematically, name the failure modes and fix the biggest ones first.
6. intermediate Evaluating RAG (retrieval-augmented generation): Measure retrieval and generation separately, so you know which half to fix.
7. advanced Evaluating agents and tool use: Measure multi-step AI agents on outcomes, the path they took, cost and safety.
8. advanced Safety, responsible AI and red-teaming: Test for harm, privacy leaks, bias and jailbreaks before attackers and journalists do.
9. advanced Online evals: A/B tests, monitoring and regression gates: Connect offline scores to real user value and catch quality drops in production.
10. advanced Eval ops: tools, cost, the AI PRD and your capstone: Run evals as a product practice: tooling, budgets, documentation and team rituals.

Browser automation means getting software, and now AI, to use websites for you: open pages, click, type, fill forms, collect data and complete tasks. Classic scripts follow fixed steps; AI browser agents take a goal in plain English and decide each step themselves.

1. basic What browser automation is (and when to use it): Understand the three generations of web automation and pick the right one for a task.
2. basic No-code browser automation: Automate simple web tasks without writing code.
3. intermediate Playwright for PMs and analysts: Read and write a simple browser script, so you can work with engineers and automate small tasks.
4. intermediate AI browser agents and computer use: Understand how AI agents use browsers and computers, and how to give them good instructions.
5. intermediate Deep research agents and web research workflows: Use AI research agents for market and competitor research, and verify what they find.
6. advanced Real workflows: PM, analyst, marketing and ops: Design end-to-end automations that combine agents, scripts and no-code tools.
7. advanced Safety, security, ethics and the law: Prevent the main risks of browser agents: injection, wrong actions, data leaks and rule-breaking.
8. advanced Evaluating and productising browser agents: Measure agent quality and write a PRD for a browser-agent feature; complete the final project.

Orchestration is how AI steps, tools and people are connected into a workflow that runs reliably; monitoring is how you know it keeps working. Start with a simple workflow and add agents only where they are needed.

1. basic Workflows vs agents: start simple: Know when a fixed workflow is enough and when an agent is worth it.
2. basic Core patterns: chaining, routing and parallelisation: Use the three most common orchestration patterns.
3. intermediate Orchestrator-workers and evaluator-optimizer: Use the two most powerful agentic patterns safely.
4. intermediate State, checkpoints and long-running work: Make workflows resumable and traceable.
5. intermediate Human-in-the-loop, approvals and error recovery: Put people at the right points and recover from failures safely.
6. advanced Multi-agent systems: Know when splitting work across agents helps, and how to coordinate them.
7. advanced Triggers, scheduling and cost control: Run workflows automatically and within budget.
8. advanced Monitoring, observability and the final project: Know when a workflow breaks or degrades, and fix it fast.

AI product strategy is deciding which problems AI should solve for your users and business, how you'll win (data, distribution, workflow, trust), and what to build, buy or partner for, before writing a single PRD.

1. basic Where AI creates value: Separate real AI opportunities from hype.
2. basic Moats and data flywheels: Understand what makes an AI product hard to copy.
3. intermediate Build vs buy vs partner, and choosing models: Make sourcing and model decisions with clear trade-offs.
4. intermediate Assessing and prioritising AI opportunities: Score AI ideas on value, feasibility and risk.
5. advanced AI roadmaps and portfolio of bets: Plan AI work under uncertainty.
6. advanced Case studies and final project: Apply the strategy tools end to end.

AI UX is designing products where outputs are probabilistic: helping users understand what AI can do, trust it the right amount, correct it easily, and recover when it's wrong.

1. basic Principles of AI UX: Design for uncertainty and the right level of trust.
2. basic Interaction patterns: Pick the right pattern for the job.
3. intermediate Trust, explainability and citations: Help users judge AI output quickly.
4. intermediate Feedback, control and personalisation: Turn user actions into learning signals.
5. advanced Failure, safety and handoff design: Design what happens when AI can't or shouldn't answer.
6. advanced Testing AI UX and final project: Validate AI experiences with users and evals.

AI features have real running costs on every use, so pricing must cover cost per task while matching the value customers get; that's why AI pricing is shifting from per-seat to usage and outcome models.

1. basic AI cost structure and unit economics: Know what each AI task costs.
2. basic Pricing models: Compare seat, usage, credits, outcome and hybrid pricing.
3. intermediate Packaging AI features: Decide free, paid and add-on AI.
4. intermediate Protecting margins: Reduce AI cost without hurting quality.
5. advanced Go-to-market for AI products: Launch and sell AI with proof.
6. advanced Final project: Price and package a real AI product.

Before LLMs, most AI in products was machine learning that predicts, classifies, ranks or recommends (fraud scores, feeds, ETAs). PMs still own these products: the problem, the data, the metric trade-offs and the lifecycle.

1. basic ML problem types: Recognise which ML problem you're solving.
2. basic Data and labelling: Get the data an ML product needs.
3. intermediate Metrics and trade-offs: Choose model metrics that match business costs.
4. intermediate Recommendations and personalisation: Understand how recommenders work and are measured.
5. advanced Model lifecycle and MLOps: Keep models working after launch.
6. advanced Working with data scientists and final project: Collaborate well and ship an ML feature.

AI governance is the set of policies, reviews and controls that make sure AI is safe, fair, legal and accountable, so teams can ship faster with fewer surprises.

1. basic Principles and risks: Know the main responsible-AI principles and risks.
2. basic Regulations to know: Understand the main laws and frameworks at a PM level.
3. intermediate AI risk and impact assessment: Assess a feature before launch.
4. intermediate Policies and documentation: Write the documents governance needs.
5. advanced Operating governance: Run governance without slowing teams down.
6. advanced Final project: Govern a real AI feature.

A platform PM builds products that other teams, developers or partners build on: APIs, SDKs, internal platforms and ecosystems. The users are developers, and the product is how easily they succeed.

1. basic Platforms and APIs as products: Understand platform types and users.
2. basic Developer experience (DX): Make developers successful fast.
3. intermediate API design decisions for PMs: Decide what matters in API contracts.
4. intermediate Ecosystems and partners: Grow a platform through others.
5. advanced Platform metrics: Measure platform health.
6. advanced AI platforms and final project: Apply platform thinking to AI.

Product operations is the function that makes product teams run smoothly at scale: shared processes, tools, data and insight pipelines, so PMs spend time on decisions instead of admin.

1. basic What product ops is: Know the scope and value of product ops.
2. basic Processes and rituals: Design lightweight rhythms.
3. intermediate Tools and data: Run the product tool stack and metrics.
4. intermediate Customer-insight pipelines: Turn feedback into prioritised insights.
5. advanced Launch management and governance: Make launches predictable.
6. advanced AI in product ops and final project: Automate product ops with AI.

Multimodal AI understands and generates more than text: images, audio and video. It powers features like reading invoices from photos, voice assistants, product images and video explainers, along with new risks like deepfakes.

1. basic Multimodal basics: Know what modern models can see, hear and create.
2. basic Vision understanding use cases: Use AI to read and interpret images.
3. intermediate Image generation in products: Use generative images responsibly.
4. intermediate Voice and video: Build with speech and video AI.
5. advanced Rights, safety, deepfakes and labelling: Manage the risks of AI media.
6. advanced Final project: Ship a multimodal feature.

Product sense, PRDs, metrics, analytics, design and interview prep.

PM interview practice

• Product Management Exercises ↗ Freemium
  PM interview questions with answers from the community
• Exponent: PM interview course ↗ Freemium
  Mock interviews, product sense, execution and estimation
• IGotAnOffer: PM interview guides ↗ Free guides
  Company-specific PM interview guides (Google, Meta, Amazon)
• Stellar Peers ↗ Freemium
  Free PM interview guides and frameworks
• SkillNavora Top 100 PM questions Free
  Model answers linked to our lessons
• SkillNavora AI mock interview Free
  Answer a PM question and get a score

Learn product management

• Product School: free resources ↗ Free
  Templates, e-books and talks from PMs at top companies
• Lenny's Newsletter ↗ Freemium
  The most-read PM newsletter: growth, PRDs, careers
• SVPG articles (Marty Cagan) ↗ Free
  Product discovery and empowered teams
• Mind the Product ↗ Freemium
  Articles and talks on every PM topic
• Atlassian Agile Coach ↗ Free
  Agile, Scrum, Kanban, roadmaps and user stories
• Scrum.org: What is Scrum ↗ Free
  The Scrum framework from the source
• Reforge ↗ Paid
  Advanced growth and product strategy programs

PRDs and documents

• ChatPRD ↗ Freemium
  AI assistant that drafts and reviews PRDs
• SkillNavora PRD library Free
  Template, framing guide and 120 PRD ideas
• SkillNavora AI PRD / BRD / FRD Writer Free
  Write any requirements document with AI
• SkillNavora AI PM Toolkit Free
  Discovery, sizing, A/B tests, launch plans and more
• PowerChords by Lazo ↗ Freemium
  PM capabilities: discovery, PRDs, sizing, launch
• Notion PRD templates ↗ Free
  Ready PRD templates to duplicate

Product tools: delivery and docs

• Jira guides ↗ Free
  Boards, backlogs, sprints and reports
• Confluence guides ↗ Free
  Docs, PRDs and team spaces
• Linear docs ↗ Free
  Issues, cycles and projects for fast teams
• Trello guide ↗ Free
  Kanban boards for simple projects
• Productboard support ↗ Free
  Feedback, prioritisation and roadmaps
• Aha! roadmapping guide ↗ Free
  Strategy, roadmaps and requirements

Product analytics

• Mixpanel docs ↗ Free
  Events, funnels, retention and cohorts
• Amplitude Academy ↗ Free
  Product analytics courses and certification
• Google Analytics 4 (Skillshop) ↗ Free
  Official GA4 courses and certification
• Hotjar help ↗ Free
  Heatmaps, recordings and surveys
• Microsoft Clarity ↗ Free
  Free heatmaps and session recordings

Design and research

• Figma Learn ↗ Free
  Interface design, prototyping and Dev Mode
• Miro Academy ↗ Free
  Workshops, journey maps and story maps
• Balsamiq: learn wireframing ↗ Free
  Wireframing basics and UI patterns
• Nielsen Norman Group articles ↗ Free
  UX research and usability, from the experts
• Google UX Design Certificate ↗ Paid / aid
  Beginner UX course (Coursera)

SQL, Excel, Python, Power BI, Tableau, statistics, ML and data interviews.

SQL: learn

• W3Schools MySQL ↗ Free
  MySQL from SELECT to JOINs with a try-it editor
• W3Schools SQL ↗ Free
  SQL basics with examples and quizzes
• SQLBolt ↗ Free
  Interactive SQL lessons in the browser
• SQLZoo ↗ Free
  Step-by-step SQL tutorial with live practice
• Mode SQL tutorial ↗ Free
  SQL for analysts, basic to advanced
• Select Star SQL ↗ Free
  An interactive SQL book with real data
• Khan Academy: Intro to SQL ↗ Free
  Video lessons and challenges

SQL: practise and interviews

• DataLemur ↗ Freemium
  SQL and data-science interview questions from real companies
• LeetCode: SQL 50 ↗ Free
  50 essential SQL interview problems
• HackerRank SQL ↗ Free
  SQL practice from easy to hard, with badges
• W3Schools SQL exercises ↗ Free
  Quick fill-in-the-blank SQL drills
• w3resource SQL exercises ↗ Free
  Hundreds of solved SQL exercises
• StrataScratch ↗ Freemium
  Real interview questions in SQL and Python
• Interview Query ↗ Freemium
  Data-science and analytics interview prep
• SkillNavora Practice Lab Free
  Run SQL in the browser and spot the trap

Excel

• Microsoft Excel training ↗ Free
  Official Excel video training
• Exceljet functions ↗ Free
  Every Excel function explained with examples
• Chandoo.org ↗ Free
  Excel, dashboards and Power Query tutorials
• W3Schools Excel ↗ Free
  Excel basics and formulas

Python and pandas

• W3Schools Python ↗ Free
  Python basics with a try-it editor
• Kaggle Learn: Python & pandas ↗ Free
  Short hands-on courses with notebooks
• Official Python tutorial ↗ Free
  The Python language, from the source
• pandas getting started ↗ Free
  Official pandas tutorials
• freeCodeCamp: Data Analysis with Python ↗ Free
  Free certification with projects
• Project Jupyter ↗ Free
  Notebooks for data analysis

Power BI and Tableau

• Microsoft Learn: Power BI ↗ Free
  Official Power BI learning paths
• Tableau free training ↗ Free
  Official Tableau training videos
• Tableau Public ↗ Free
  Publish dashboards and learn from others
• SQLBI (DAX) ↗ Freemium
  DAX and data modelling articles and videos

Statistics and machine learning

• Google Machine Learning Crash Course ↗ Free
  Fast ML introduction with exercises
• Coursera: Machine Learning (Andrew Ng) ↗ Paid / audit
  The classic ML specialization
• Khan Academy Statistics ↗ Free
  Statistics and probability, step by step
• scikit-learn tutorials ↗ Free
  Official ML library tutorials
• fast.ai ↗ Free
  Practical deep learning for coders
• Kaggle competitions ↗ Free
  Practise on real datasets and notebooks
• StatQuest (YouTube) ↗ Free
  Statistics and ML explained simply

Business analysis

• SkillNavora BRD & FRD guide Free
  Templates, techniques and 25 project ideas
• IIBA BABOK ↗ Paid
  The business analysis standard
• Modern Analyst ↗ Free
  BA articles, templates and interview questions

Prompting, LLM apps, agents, MCP and the everyday AI tools.

Learn GenAI

• Claude prompt engineering guide ↗ Free
  Official prompting techniques from Anthropic
• Anthropic Learn ↗ Free
  Courses and guides for using Claude
• DeepLearning.AI short courses ↗ Free
  1-hour courses on LLMs, RAG and agents
• Hugging Face Learn ↗ Free
  LLM, agents and NLP courses
• Prompting Guide ↗ Free
  Prompt techniques with examples
• Learn Prompting ↗ Freemium
  Beginner-friendly prompt engineering course
• Google AI Essentials ↗ Paid / aid
  Practical AI skills for work (Coursera)
• Elements of AI ↗ Free
  AI basics for everyone, no coding

Build with LLMs and agents

• OpenAI Cookbook ↗ Free
  Code examples for LLM apps
• LangChain Academy ↗ Free
  Free courses on LangGraph and agents
• Model Context Protocol (MCP) ↗ Free
  Connect AI assistants to tools and data
• Claude Code docs ↗ Free
  Agentic coding in the terminal
• GitHub Copilot docs ↗ Freemium
  AI pair programming
• Cursor docs ↗ Freemium
  AI code editor

AI assistants (help centres)

• Claude ↗ Freemium
  Writing, analysis, coding, projects
• ChatGPT ↗ Freemium
  OpenAI's assistant: help and guides
• Google Gemini ↗ Freemium
  Gemini help centre
• Perplexity ↗ Freemium
  AI search with sources
• NotebookLM ↗ Free
  Chat with your documents, audio overviews
• DeepSeek ↗ Free
  Open-weight AI models and chat
• Grok ↗ Freemium
  xAI's assistant

AI for meetings and writing

• Otter.ai help ↗ Freemium
  Meeting transcription and summaries
• Fireflies.ai ↗ Freemium
  AI meeting notes and search
• Grammarly ↗ Freemium
  AI writing help
• Microsoft Copilot ↗ Paid
  AI in Word, Excel, PowerPoint and Teams

AI images, video and voice

• Midjourney docs ↗ Paid
  Prompting for AI images
• Adobe Firefly ↗ Freemium
  AI images and generative fill
• Leonardo.Ai ↗ Freemium
  AI images and assets
• Ideogram ↗ Freemium
  AI images with good text in images
• Runway Academy ↗ Free
  AI video tutorials
• ElevenLabs docs ↗ Freemium
  AI voice generation and voice agents

Build apps, websites and automations without heavy coding (for every program).

App builders

• Lovable docs ↗ Freemium
  Build web apps by chatting
• Replit docs ↗ Freemium
  Build and deploy apps with AI
• Bolt ↗ Freemium
  Build full-stack apps in the browser
• v0 by Vercel ↗ Freemium
  Generate UI and apps from prompts
• Bubble Academy ↗ Free
  No-code web apps
• Webflow University ↗ Free
  Design and build websites

Automation

• n8n courses ↗ Free
  Workflow automation and AI agents
• Zapier Learn ↗ Free
  Automate apps without code
• Make Academy ↗ Free
  Visual automation scenarios
• Apify Academy ↗ Free
  Web scraping and automation
• SkillNavora n8n tutorial Free
  Our complete n8n guide

Design and content

• Canva Design School ↗ Free
  Design basics and Canva tutorials
• Adobe Express ↗ Freemium
  Quick social graphics and videos
• Frame.io ↗ Freemium
  Video review and collaboration
• Epidemic Sound ↗ Paid
  Royalty-free music for videos

Data structures, algorithms, Git and coding practice (used in Data and GenAI tracks).

Practise

• LeetCode ↗ Freemium
  Coding interview problems by company and topic
• NeetCode roadmap ↗ Free
  The 150 most important problems, with videos
• HackerRank ↗ Free
  Coding practice and certifications
• GeeksforGeeks DSA ↗ Free
  DSA tutorials and practice
• SkillNavora DSA handbook Free
  Our DSA guide

Learn to code

• Harvard CS50 ↗ Free
  The best intro to computer science
• freeCodeCamp ↗ Free
  Free certifications in web, Python and data
• The Odin Project ↗ Free
  Full-stack web development path
• GitHub Skills ↗ Free
  Learn Git and GitHub hands-on
• Pro Git book ↗ Free
  Git explained, free online

SFMC, digital marketing, content creation, FDE and public speaking.

SFMC and CRM

• Salesforce Trailhead ↗ Free
  Free official Salesforce and Marketing Cloud trails
• HubSpot Academy ↗ Free
  Inbound marketing, email and CRM courses

Digital marketing

• Google Skillshop ↗ Free
  Google Ads and Analytics certifications
• Meta Blueprint ↗ Free
  Facebook and Instagram ads courses
• Semrush Academy ↗ Free
  SEO, content and PPC courses
• Ahrefs Academy ↗ Free
  SEO courses for beginners

Content creation

• YouTube Creators ↗ Free
  Official tips for growing a channel
• Canva Design School ↗ Free
  Design for social media
• LinkedIn Creator tips ↗ Free
  Grow on LinkedIn

Forward Deployed Engineering

• AWS Skill Builder ↗ Free
  Cloud fundamentals and architecture
• Postman Academy ↗ Free
  APIs and integrations
• Docker get started ↗ Free
  Containers for deploying apps

Public speaking and English

• Toastmasters ↗ Paid
  Practise speaking in clubs across India
• BBC Learning English ↗ Free
  Free English lessons, grammar and pronunciation
• Cambridge English: learning ↗ Free
  Free English activities
• TED: talks on speaking ↗ Free
  Learn from the best talks
• SkillNavora AI Speaking Coach Free
  Speak and get instant feedback

• SkillNavora_Data_Science_AI_Complete_Handbook_Part1.pdf 15.2 MB
• SkillNavora_Data_Science_AI_Complete_Handbook_Part2.pdf 11.6 MB
• SkillNavora_Data_Science_AI_Complete_Handbook_Part3.pdf 10.5 MB
• SkillNavora_Data_Science_AI_Complete_Handbook_Part4.pdf 7.0 MB
• Complete-PM-Master-Handbook.pdf 21.9 MB
• Complete-PM-Master-Handbook_Part1.pdf 9.1 MB
• Complete-PM-Master-Handbook_Part2.pdf 8.8 MB
• Interview-Handbook.pdf 1.2 MB
• SkillNavora_GenAI_Launchpad_Handbook.pdf 18.8 MB

• Track_01_Advanced_Excel.pdf 8.8 MB
• Track_02_SQL_for_Data_Analysis.pdf 9.6 MB
• Track_03_Power_BI.pdf 4.1 MB
• Track_04_Tableau.pdf 3.0 MB
• Track_05_AI_for_Data_Analysis.pdf 2.6 MB
• Track_06_Python_for_Data_Science.pdf 15.1 MB
• Track_07_Statistics_Machine_Learning.pdf 14.2 MB
• Track_08_Generative_AI_Agentic_AI.pdf 5.6 MB
• Track_09_AI_Agents_MCP_APIs_for_PMs_and_BAs.pdf 2.5 MB
• Track_10_AI_No_Code_Tools_Lab.pdf 1.5 MB
• Track_11_Capstone_Portfolio_Interviews.pdf 1.3 MB
• Track_12_Salesforce_Marketing_Cloud_SFMC.pdf 0.9 MB
• Track_13_Digital_Marketing.pdf 0.8 MB
• Track_14_Content_Creation.pdf 0.8 MB
• Track_15_Forward_Deployed_Engineer_FDE.pdf 0.8 MB
• Track_16_Public_Speaking.pdf 0.7 MB

• AI_Builder_Tools.pdf 0.5 MB
• AI_Engineer_Complete_Path.pdf 0.7 MB
• AI_Evals_for_Product_Managers.pdf 0.5 MB
• AI_Governance_and_Responsible_AI.pdf 0.4 MB
• AI_Product_Strategy.pdf 0.5 MB
• AI_Second_Brain.pdf 0.5 MB
• AI_Skills_and_Templates.pdf 0.4 MB
• Agent_Orchestration_and_Monitoring.pdf 0.4 MB
• Browser_Automation_and_AI_Agents.pdf 0.4 MB
• Designing_AI_Experiences.pdf 0.4 MB
• ML_Products_for_PMs.pdf 0.4 MB
• Multimodal_and_AI_Media.pdf 0.4 MB
• Platform_and_API_Product_Management.pdf 0.4 MB
• Pricing_and_Monetising_AI.pdf 0.4 MB
• Product_Operations.pdf 0.4 MB
• Prompt_and_Context_Engineering.pdf 0.4 MB
• Web_Automation_Webhooks_Triggers_Playwright_MCP.pdf 0.6 MB

• SkillNavora_BRD_Template.doc 0.0 MB
• SkillNavora_FRD_Template.doc 0.0 MB
• SkillNavora_PRD_Template.doc 0.0 MB

• ai-de.pdf 0.3 MB
• ai-pm.pdf 0.3 MB
• genai-launchpad.pdf 0.3 MB