Build Your AI Product Analyst
See what an AI product analyst can do and how it works through live demos. We walk through the possibilities in tools you already use, like Google Sheets and Slides, the Claude Code building blocks (skills, agents, hooks, MCP), and packages in Claude Cowork, so you leave with the what, the how, and a take-home resource each session. Sign up for all, get every recording.
By continuing, you agree to Maven's Terms and Privacy Policy.
Wed Jul 8·5:00 PM UTC
Claude Code 101: Learn what Skills, Agents, and Hooks are
Claude Code has a lot of moving parts, and most people stall before they start because they cannot tell a skill from an agent from a hook. The pieces are simple once someone maps them for you. This session is that map: what each building block is, when to use it, and how they orchestrate into a working AI analyst.
You'll learn from
Shane Butler
Co-founder, AI Analyst Lab
Sravya Madipalli
Senior DS Leader (Ex-Microsoft)
Hai Guan
Head of Data at Ontra, Ex-LinkedIn
Wed Jul 22·5:00 PM UTC
Product Analytics 101: From Question to Decision with AI
Most analysis never leads to a decision. It stalls in a dashboard, a deck, or a "let me look into it." Getting the answer stopped being the hard part once AI could crunch the data. The hard part is asking the right question and knowing when the answer is good enough to act on. This session is the full workflow from a fuzzy ask to a decision, using AI.
You'll learn from
Shane Butler
Co-founder, AI Analyst Lab
Sravya Madipalli
Senior DS Leader (Ex-Microsoft)
Hai Guan
Head of Data at Ontra, Ex-LinkedIn
Wed Jul 29·5:00 PM UTC
Build Google Slides from Data with AI
What if your analysis could turn itself into a clean deck? The slow part of a readout was never the thinking, it was the hours spent formatting charts, wording titles, and lining up boxes. AI can now do that part in minutes, which means the real skill is telling the story clearly. This session is the full workflow from data to a presentation-ready Google Slides deck with AI
You'll learn from
Shane Butler
Co-founder, AI Analyst Lab
Sravya Madipalli
Senior DS Leader (Ex-Microsoft)
Hai Guan
Head of Data at Ontra, Ex-LinkedIn
Wed Aug 5·5:00 PM UTC
Build the Context That Makes AI Data Agents Reliable
Ask an AI the same data question five times and you can get five answers. That is not a model problem, it is a context problem: the agent guesses your metric's meaning differently each run. This session is why agents drift and how one clear definition makes them reliable. You write the contract that stops the drift and watch the answers converge on a single number your whole team can trust.
You'll learn from
Shane Butler
Co-founder, AI Analyst Lab
Sravya Madipalli
Senior DS Leader (Ex-Microsoft)
Hai Guan
Head of Data at Ontra, Ex-LinkedIn
Wed Aug 12·7:00 PM UTC
Test Kimi and Open Models on Real Analytics Work
The AI model behind your AI analyst is a decision most builders never make on purpose. They default to the biggest name and pay for it on every run. Open models now do analyst-grade work at a fraction of the price and needed privacy, but nobody shows you a fair test on real work. This session is that test: same tasks, head to head, graded on quality, cost, and speed, so you pick with evidence.
You'll learn from
Shane Butler
Co-founder, AI Analyst Lab
Sravya Madipalli
Senior DS Leader (Ex-Microsoft)
Hai Guan
Head of Data at Ontra, Ex-LinkedIn
Wed Aug 19·5:00 PM UTC
Build a Semantic Layer So AI Defines Your Metrics
Everyone on your team defines retention differently, and AI makes that worse. Ask three people, or three chat sessions, and you get three numbers, all confidently wrong. The fix is one place that says what each metric means and how tables connect: a semantic layer. Once it exists, AI stops guessing and computes your metrics your way, every time. This session builds a starter one live.
You'll learn from
Shane Butler
Co-founder, AI Analyst Lab
Sravya Madipalli
Senior DS Leader (Ex-Microsoft)
Hai Guan
Head of Data at Ontra, Ex-LinkedIn
Wed Aug 26·5:00 PM UTC
Claude Cowork 101: Build Your First AI Data Analyst
Building an AI analyst used to mean a terminal, a repo, and a setup marathon that lost most people before their first insight. Claude Cowork changes that. You assemble plugins and packages in the browser, point them at your data, and you have an analyst that reads, analyzes, and reports. This session shows you how to build that first analyst, run a real analysis with no code, and share it out.
You'll learn from
Shane Butler
Co-founder, AI Analyst Lab
Sravya Madipalli
Senior DS Leader (Ex-Microsoft)
Hai Guan
Head of Data at Ontra, Ex-LinkedIn
Wed Sep 2·5:00 PM UTC
Claude Code 101: Ground Claude in Your Business Data
AI does not know your business until you teach it. Ask a fresh model about your numbers and it guesses what "active" means, invents a table name, or answers the wrong question. The fix is not a better prompt every time, it is giving Claude your context once: your tables, your terms, and what your metrics mean. This session shows you how, live, and you leave with a starter kit for your own setup.
You'll learn from
Shane Butler
Co-founder, AI Analyst Lab
Sravya Madipalli
Senior DS Leader (Ex-Microsoft)
Hai Guan
Head of Data at Ontra, Ex-LinkedIn
Wed Sep 9·5:00 PM UTC
Build a Self-Repairing Context Loop for AI Data Agents
Most AI analysis quietly rots: a metric gets redefined, the agent keeps answering from stale context, and nobody notices until the number is wrong. The fix is not more prompting. It is a loop where the agent detects the drift, repairs its own definitions in the repo, and re-runs until variance collapses. We build that loop live, so you watch the agent catch itself and land on one honest answer.
You'll learn from
Shane Butler
Co-founder, AI Analyst Lab
Sravya Madipalli
Senior DS Leader (Ex-Microsoft)
Hai Guan
Head of Data at Ontra, Ex-LinkedIn
Wed Sep 16·7:00 PM UTC
Data Storytelling 101: Build an Exec Readout with AI
Great analysis gets ignored when the story is buried. Getting the answer stopped being the hard part once AI could crunch the data. The hard part is landing it: turning a pile of charts into a readout that makes a busy exec decide. This session is the workflow: lead with the insight, structure the problem, insight, and ask, take a position, and anticipate the pushback before it lands.
You'll learn from
Shane Butler
Co-founder, AI Analyst Lab
Sravya Madipalli
Senior DS Leader (Ex-Microsoft)
Hai Guan
Head of Data at Ontra, Ex-LinkedIn
Wed Sep 23·5:00 PM UTC
Ace Analytics Interviews with AI
Analytics interviews are hard, and prepping alone by rereading notes never simulates thinking out loud while someone probes your reasoning. AI is the study partner you wish you had: it plays the interviewer, asks real product sense and case questions, and tells you where your logic breaks. This session is how to prep with AI, keep it honest, and leave with a loop you can run before the real thing.
You'll learn from
Shane Butler
Co-founder, AI Analyst Lab
Sravya Madipalli
Senior DS Leader (Ex-Microsoft)
Hai Guan
Head of Data at Ontra, Ex-LinkedIn
Wed Sep 30·5:00 PM UTC
Spreadsheets 101: Analyze Any Sheet with AI
That messy spreadsheet you have been avoiding? AI can analyze it in minutes. The barrier was never the data, it was the tooling: pivot tables, formulas, the wait on a data team. That barrier is gone. The new skill is knowing how to ask, and how to tell whether the answer is right. This session is how to get real analysis from any sheet, no formulas: clean it, chart it, check it, and recommend.
You'll learn from
Shane Butler
Co-founder, AI Analyst Lab
Sravya Madipalli
Senior DS Leader (Ex-Microsoft)
Hai Guan
Head of Data at Ontra, Ex-LinkedIn
Wed Oct 7·5:00 PM UTC
Metrics 101: Define a North Star with AI
Most North Star metrics are vanity metrics in disguise. They climb on a slide while retention sits flat, and a whole quarter gets aimed at the wrong number. AI can pressure-test yours in minutes: it checks the definition, tests whether it leads or lags, and breaks it into levers you can move. This session is the workflow for defining a North Star that holds up, and you leave with a checklist.
You'll learn from
Shane Butler
Co-founder, AI Analyst Lab
Sravya Madipalli
Senior DS Leader (Ex-Microsoft)
Hai Guan
Head of Data at Ontra, Ex-LinkedIn
Wed Oct 14·5:00 PM UTC
Trust Your AI Analytics: Know When the Number Is Right
AI output looks the same whether it is right or wrong. It is fluent and confident either way, and that is the trap. Getting an answer stopped being the hard part. The hard part is knowing whether to trust it before it lands in a deck or a decision. This session is the quick checks: spot the confident wrong result, run tests that need no answer key, and know when a number is good enough to act on.
You'll learn from
Shane Butler
Co-founder, AI Analyst Lab
Sravya Madipalli
Senior DS Leader (Ex-Microsoft)
Hai Guan
Head of Data at Ontra, Ex-LinkedIn
Wed Oct 21·5:00 PM UTC
Experimentation 101: Run an A/B Test with AI
You'll learn from
Shane Butler
Co-founder, AI Analyst Lab
Sravya Madipalli
Senior DS Leader (Ex-Microsoft)
Hai Guan
Head of Data at Ontra, Ex-LinkedIn
Wed Oct 28·5:00 PM UTC
Causal Experimentation 101: Prove Impact Without an A/B Test
Most impactful questions never get a clean A/B test. The feature shipped, the change hit everyone at once, or the sample is too small. Pre-post, diff-in-diff, and matching let you estimate real impact from your data, and AI makes running them fast. The hard part is picking the right method and catching the confounders that break your claim. This is the no-experiment causal toolbox, made simple.
You'll learn from
Shane Butler
Co-founder, AI Analyst Lab
Sravya Madipalli
Senior DS Leader (Ex-Microsoft)
Hai Guan
Head of Data at Ontra, Ex-LinkedIn