Our Promise: in 6 weeks, this is who you become
-
Today you write SQL one question at a time. Week 6: you build a SQL assistant that answers leadership’s standing questions, scored against a golden question set.
-
Today you build dashboards on data someone else loaded. Week 6: you build the pipeline on Fabric and a guarded, self-serve data app on top of it.
-
Today you ask AI and hope it’s right. Week 6: you catch its confident wrong answers with golden sets, known totals and eval scores, before leadership does.
-
Today you present numbers. Week 6: you forecast churn, test it against a baseline, and turn it into the one-slide recommendation a CFO can act on.
-
Today someone else scopes the project and runs the team. Week 6: you write the charter, run the AIMS grid meeting, estimate the work, delegate, and hire with a scorecard.
-
Today you run reports by hand. Week 6: your analytics agents watch the data and flag problems for you.
-
Today you wait for your work to be noticed. Week 6: you pitch your GreenPlate Command Center to a leadership panel that pushes back.
Overview
What you'll learn in
this Live Advanced Data Analyst Bootcamp
Week-1: Get started with AI
AI Landscape & SQL
-
Session 1 - Day One at GreenPlate FoodTech: Kickoff and the AI Landscape (Sat 21st Nov)
The Day One email from the CEO · Company briefing: 12 cities, the Fresh pilot, five function heads, the warehouse · The analytics manager JD vs the 2026 JD · The AI landscape for analysts: assistants, Copilots, coding agents, automation, MCP · How LLMs work, just enough · What never goes into a prompt · Workspace setup · Scenario: the confident wrong answer
Output: A working AI workspace and your first-week plan as the Data Analytics Manager
-
Session 2 - Build Day: Your SQL Assistant Answers Leadership's Ten Questions (Sun 22nd Nov)
Why a bare LLM writes wrong SQL on a real warehouse · Claude Projects with instructions and knowledge files · Loading schema, metric definitions and worked queries · Answering leadership's ten standing questions · The golden question set · Where it fails and how you catch it · Scenario: the forgotten refund filter
Output: Tool 1 of 5. A schema-aware SQL assistant, scored against a golden question set
Week-2: Plan the project
Planning & Claude Code
-
Session 3 - Project Planning the Corporate Way: Charter, AIMS Grid, Estimation (Sat 28th Nov)
How a project really starts in a company · The project charter · The AIMS grid meeting, run live in pods as Marketing, Finance, Ops and Supply Chain · Stakeholder mapping and the decision contract · Estimation: work breakdown, three-point estimates, buffers · Personal branding and a 90-day plan · Scenario: the project estimate conundrum
Output: A charter, an AIMS grid and an estimate leadership signs off, plus your 90-day LinkedIn plan
-
Session 4 - Claude Code: The Expansion Simulator That Ends the Marketing vs Finance Fight (Sun 29th Nov)
Marketing's model vs finance's model · Claude Cowork turns forty kitchen files into unit economics, with row counts reconciled · Designing the levers: budget by channel, CAC, kitchens, price, delivery fee, churn · Claude Code builds the simulator web app with Excel export · Verifying against one real month · Scenario: the simulator that flattered marketing
Output: Tool 2 of 5. An expansion simulator both teams trust
-
Jamming Session 1 (optional) - Office Hours with Hem, Naveen and Aditya (Wed 2nd Dec, 8:00 to 9:30 PM IST)
Questions on the SQL assistant and the simulator · Debugging together · Recorded
Output: Both tool builds unblocked before Phase 2 continues
Week-3: Build pipelines and apps
Fabric & Claude Code
-
Session 5 - Analytics Pipelines on Fabric: The Payments Feed Finance Could Not Reconcile (Sat 5th Dec)
Fabric workspace, Lakehouse and SQL endpoint · VS Code with Claude Code · The daily orders pipeline: ingest, clean, load, schedule, refresh Power BI · Connecting a payment gateway sandbox API · Reconciling orders to payments · Power BI Copilot writes the DAX, you verify it · Fixing a failed run · Scenario: the 1.8 crore payments gap
Output: Tool 3 of 5. A scheduled payments pipeline finance can reconcile
-
Session 6 - Building the Data Genie App with Claude Code (Sun 6th Dec)
Self-serve downloads for marketing and sales · Writing the spec: tables, filters, metrics, guardrails, row limits · Spec to working app with Claude Code · Read-only warehouse connection · Every query and download logged · A natural-language question box with a golden set · Scenario: forty download requests a week
Output: Tool 4 of 5. A guarded self-serve data app with an eval score
-
Jamming Session 2 (optional) - On-Call Debrief with Hem, Naveen and Aditya (Wed 9th Dec, 8:00 to 9:30 PM IST)
What broke and how you found it · Pipeline and Data Genie questions · A walkthrough of the churn data · Recorded
Output: Ready for the ML session with the churn data understood
Week-4: Forecast and present
ML & Storytelling
-
Session 7 - Machine Learning for Analysts: Predicting Churn by City with Regression (Sat 12th Dec)
When a rule beats a model · Framing churn per zone per week, with two baselines · Regression with scikit-learn: AI writes, you read · Reading coefficients out loud · Residuals by city · Spotting leakage and extrapolation in someone else's model · Reading an A/B test honestly · Scenario: the model that knows the future
Output: Tool 5 of 5. A churn forecast that beats its baselines, with a review memo
-
Session 8 - Data Storytelling: Presenting to Stakeholders, and the Capstone Brief (Sun 13th Dec)
Answer first: the pyramid principle and SCQA · One chart, one message · The one-slide recommendation · What a CFO reads first vs a CMO · Executive Q&A and handling disagreement · AI-drafted summaries: keep, check, never send · The quarterly review pre-read, presented in pods · Capstone brief opened
Output: An executive deck and a five-minute readout leadership believes
Week-5: Lead the Team, build agents
Leadership & Agents
-
Session 9 - Running an Analytics Team: Cadence, Delegation, Estimation, Hiring (Sat 19th Dec)
Where a manager's week goes · The intake queue and task planning · Estimating a real backlog against a fixed quarter · The weekly cadence: standup, review, retro · Delegation and managing up · Reviewing SQL, dashboards and analysis · Hiring with scorecards · The first 90 days as a manager · Scenario: the over-committed quarter
Output: A quarter plan, a hiring scorecard and your 90-day manager plan
-
Session 10 - Building Analytics Agents, and the Command Center They Live In (Sun 20th Dec)
What makes an agent: goal, tools, loop, verification · When an agent beats a flow · A weekly insight report agent · A data-quality watchdog agent · A competitor price watch agent · The Command Center dashboard, built with Claude Code · Evals, guardrails, cost caps and audit logs · Scenario: the agent that lied on Tuesday · The unguided capstone starts here
Output: Scheduled, guarded analytics agents inside a dashboard you built
-
Jamming Session 3 (optional) - Capstone Jamming with Hem, Naveen and Aditya (Wed 23rd Dec, 8:00 to 9:30 PM IST)
Implementation questions on your capstone · Design review · Debugging together · Recorded
Output: Your capstone unblocked before the review weekend
Week-6: Pitch on demo day
Capstone & Demo Day
-
Session 11 - Capstone Review: Harden It, Test It, Learn to Pitch It (Sat 26th Dec)
Design review of every Command Center · Debugging the failures we see most · Evals against the golden sets · Hardening: guardrails, cost, audit log, handover README · How to pitch to leadership, rehearsed in pods · Packaging your analyst skill library · Your portfolio website, published on GitHub Pages
Output: A demo-ready capstone, 20+ packaged analyst skills and a live portfolio website
-
Session 12 - Demo Day: Pitch the Command Center to the Leadership Panel, and Graduate (Sun 27th Dec)
Capstone pitches to the GreenPlate leadership panel · Writing your own promotion case · The analytics manager interview loop · Portfolio, GitHub and LinkedIn as an advanced data analyst · Graduation
Output: A five-minute pitch you have defended, and a promotion case backed by six weeks of shipped work
Learn From
The People Who Run Analytics Teams
Hemanand Vadivel
Co-Founder & CEO, Codebasics
Leads most sessions and every leadership and management block.
I was among the top 1% with my amazing data analytics job in the UK. I left the job to stay back in India and pursue something that gives me a better sense of being and more joy - creating a positive impact on society by sharing knowledge.
Naveen S
Head of Data Analytics, Codebasics
Plays the GreenPlate COO. He is the one who will not accept a dashboard as an answer.
From a Tamil medium school and a Biomedical degree to Test Engineer at Infosys, I moved into data with no CS degree or connections, just by learning in public. In 4 years at Codebasics, I grew to Head of Content and Analytics. To me, AI has senior-level intelligence and intern-level reliability but it needs a data pro who knows what good looks like.
Aditya Goel
Business Automation Specialist & Learner Experience Lead, Codebasics
Backs the build sessions. Runs the jamming sessions with Hem and Naveen.
I come from a non-tech background and took a different route into data analytics. It has been 3+ years since I started this journey. Coming from a non-tech world gave me a fresh view of data and the stories it tells. Over time I moved into automation too. I started cutting down repetitive steps in my work, which gave me more time to find insights and understand the business. With AI in the picture, it is now about how to keep improving and optimizing the way you work. What I have learned is that anyone can learn the tools if they want to. Problem solving and finding better ways to work is what gives you the edge.
Dhaval Patel
Founder, Codebasics · Ex-NVIDIA
Curriculum advisor. Sets what this cohort teaches and what it refuses to.
I have 17 years of experience in programming and data science at leading tech companies like NVIDIA and Bloomberg. I also run Codebasics, a leading YouTube channel for data science, ML, and data structures. I believe "anyone can code", so I use analogies, simple explanations, and step-by-step storytelling to make complex concepts easy to understand, even for high school students.
The Stack
The tools senior analysts actually use in 2026
Claude
PRD drafting and Claude Code
Claude Code
Building the five tools
Claude Cowork
Multi-file cleaning
Microsoft Fabric
Lakehouse and pipelines
Power BI · Reporting
Reports and verified DAX
SQL
The warehouse
Python + Scikit-Learn
The churn regression
GitHub + VS Code
Where the work livesHear It From
Our Happy Learners
Our content is rated 4.9/5 from 8680+ Learners
Python
The Data Engineering Basics for Data Analysts course provides a strong foundation in core data engineering concepts with a practical, hands-on approach. I particularly enjoyed building an end-to-end ETL pipeline using AWS services such as S3, Glue, Lambda, Athena, and Redshift. The explanations were clear, the projects were relevant, and the course effectively connected theory with real-world implementation.
This course helped me better understand how modern data pipelines are built and managed in the cloud. I highly recommend it to data analysts, aspiring data engineers, and professionals looking to strengthen their AWS data engineering fundamentals.
Highly recommended! 🌟
This is my third consecutive course with Codebasics with Dahaval Sir. I am really happy to take these courses which gave me a good understanding and solid foundation on AI-ML and Data Engineering.
The data engineering course gave me a real good exposure to how data preperation is done in AWS. But becuase i didnt have any knowledge on AWS so i couldnt run the code properly on LAMBDa, Glue and Atehna , got some errors which i could not fix.... I had to take a detailed course on AWS and understood how AWS work. I guess there will be many students who will face the same problem when they will landup in this course...so my humble request is in this Data engineering course please add some more tutorial videos on AWS at the begining, even you start the actual Data pipeline....Rest all good. And please make a detailed course on Docker and Kubernetes and how to run ML app on them in AWS. Thanks a lot....
This course provides a comprehensive introduction to the Python programming language. The course is well structured, starting with the basics and gradually building up to more advanced concepts. The lessons are taught through clear and concise video tutorials, accompanied by interactive coding exercises that reinforce the concepts covered. The course covers topics such as data types, functions, object-oriented programming, and more. The instructor is knowledgeable and passionate about Python, and the course is well-paced, making it easy to follow along and absorb the material. Overall, the Code Basics Python course is an excellent resource for anyone looking to learn Python, from beginners to those with some programming experience.
Landed a Job
Hello CodeBasics team and fellow students!
I’ve just completed the Python course from the GEN-AI bootcamp, and I really want to thank Mr. Patel for conducting such engaging lectures and practical sessions. I had the chance to apply what I learned on two real-life projects (I’m saying two because some projects were excluded in GEN-AI, but these two were highly relevant).
The exercises after each unit were a great way to reinforce learning. My advice: take this course and practice consistently. Once you finish the course, keep practicing to truly master the concepts.
Thank you, CodeBasics! I’m proud to be part of this family and to have completed the first step in my GEN-AI/Data Science journey.
Landed a Job
I took the Data Engineering Basics for Data Analysts course on codebasics.io 🚀
Solid intro to DE concepts. Thank you Dhaval Patel for explaining the basic concepts clearly with examples — really appreciate your style of teaching.
Great starting point for data analysts curious about data engineering. Worth it! 👍
The Codebasics Promise
Build, Check & Defend Real Analytics Work in 6 Weeks.
Not a tutorial. Five working tools and an unguided capstone, pitched to a leadership panel that pushes back.
| What you get | Recorded course | Generic AI bootcamp | This cohort |
|---|---|---|---|
| Live, mentor-led sessions | |||
| Data you work on | Sample files | Toy datasets | 20M order lines |
| The 2026 AI analyst stack | On your own | Often generic | |
| Certificate of completion | |||
| Investment | Your time | Usually far higher | US$420 |
May we help you?
Frequently Asked
Questions
Q.1
When does the bootcamp officially start?
Q.2
When do I get access after enrolling as an Inner Circle member?
Q.3
What is the Inner Circle, and how is it different from regular enrollment?
Q.4
What will I build in this bootcamp?
Q.5
When are the live sessions?
Q.6
What if I miss a live session?
Q.7
What happens after the 42 days? Do I lose access?
Q.8
Is the Data Analytics Bootcamp 6.0 included in this cohort?
If you need to brush up, the cohort includes pre-work refreshers and the Data Analytics fundamentals courses to help you prepare.
Q.1
Do I need prior experience?
Q.2
I am a fresher with no work experience. Can I join?
Q.3
Who is this bootcamp designed for?
Q.1
How do I get help if I am stuck?
Q.2
Is there job assistance?
Q.1
What is the Inner Circle price and when does it close?
Q.2
I already own a Codebasics Data Analytics Bootcamp or some courses from it. What do I pay?
Q.1
I used a subsidy and now want to refund this Bootcamp itself. What happens?
Q.2
I used a subsidy (my existing Data Analytics Bootcamp or individual course purchase). Can I refund my original purchase after enrolling?
Q.3
What is the refund policy?
Please note: The refund window is based on the two live sessions scheduled after your enrollment, not on whether you attended them. If you miss a session, the refund window still moves forward.
To request a refund, email [email protected] before the window closes.
Please read the full refund policy here.
Q.1
When does the bootcamp officially start?
Q.2
When do I get access after enrolling as an Inner Circle member?
Q.3
What is the Inner Circle, and how is it different from regular enrollment?
Q.4
What will I build in this bootcamp?
Q.5
When are the live sessions?
Q.6
What if I miss a live session?
Q.7
What happens after the 42 days? Do I lose access?
Q.8
Is the Data Analytics Bootcamp 6.0 included in this cohort?
If you need to brush up, the cohort includes pre-work refreshers and the Data Analytics fundamentals courses to help you prepare.
Q.1
Do I need prior experience?
Q.2
I am a fresher with no work experience. Can I join?
Q.3
Who is this bootcamp designed for?
Q.1
How do I get help if I am stuck?
Q.2
Is there job assistance?
Q.1
What is the Inner Circle price and when does it close?
Q.2
I already own a Codebasics Data Analytics Bootcamp or some courses from it. What do I pay?
Q.1
I used a subsidy and now want to refund this Bootcamp itself. What happens?
Q.2
I used a subsidy (my existing Data Analytics Bootcamp or individual course purchase). Can I refund my original purchase after enrolling?
Q.3
What is the refund policy?
Please note: The refund window is based on the two live sessions scheduled after your enrollment, not on whether you attended them. If you miss a session, the refund window still moves forward.
To request a refund, email [email protected] before the window closes.
Please read the full refund policy here.
Begin Your Journey