Build AI Analysts in Claude Code
Shane Butler
Principal Data Scientist @ Ontra
Hai Guan
Head of Data @ Ontra AI | Ex-LinkedIn
.png&w=768&q=75)
.png&w=768&q=75)
Build agentic data analysts for your company in one weekend. No code.
This is a hands-on weekend bootcamp (4 hours Saturday, 4 hours Sunday) where you build AI analysts powered by Claude Code. Not a lecture series. Not a demo you watch. You set up your own environment, build custom skills and agents, connect to real data, and leave with a working system that turns business questions into charts, narratives, and presentations in minutes.
No Python. No SQL. No coding of any kind. Claude Code writes all the code. You direct the analysis.
By Sunday evening, you will have a complete AI analyst repo on your computer: 11 skills, 15 agents, data connections, and a finished analysis you can share with your manager Monday morning. Everything runs locally. No vendor lock-in. No proprietary platform. Just a repo you own.
AI is changing how teams make decisions with data. The bottleneck is no longer the analysis — it is knowing how to set up the tools. This bootcamp gives you that setup in a weekend. You will not learn about agentic systems. You will build one.
What you’ll learn
Leave with a working AI analyst system on your laptop (skills, agents, data connections) and a finished analysis ready for Monday.
Install Claude Code, configure a custom CLAUDE.md, and connect to a data warehouse, all running by lunch on Day 1.
No terminal experience needed. We walk through every step with three instructors troubleshooting live.
Run your first AI-powered analysis in minutes and see the full pipeline working end to end.
Create skills for chart styles, data quality checks, question framing, and metric specs. All simple text files you edit.
Apply Storytelling with Data visualization patterns automatically to every chart Claude Code generates.
Extend or modify any skill after the bootcamp; no code, no dependencies, just markdown.
Create agents for hypothesis generation, descriptive analytics, root cause investigation, and storytelling.
Chain agents together: business question → analysis → charts → narrative → presentation, in one command.
Customize agent prompts to match your team's data, terminology, and standards.
Run your full agent chain on real data and get validated findings, not toy examples.
Generate publication-quality charts with action titles, annotations, and consistent styling.
Output a slide deck with speaker notes you can present to stakeholders the same week.
Bring your own dataset (warehouse, CSV, or API) and connect it live during the final session.
Run the same agents on your data and produce an analysis your manager can actually use.
Pass the Monday Morning Test: open the repo at work, ask a question, get an answer.
Learn directly from expert instructors
.png&w=384&q=75)
.png&w=384&q=75)
Who this course is for
Product managers who are tired of waiting in the data team's queue. Stop waiting. Analyze it yourself.
Data scientists who want to multiply their output. You know how to do the analysis manually. Now automate it.
Engineers who want to make data-driven decisions without hiring a data team.
What's included
Live sessions
Learn directly from your instructors in a real-time, interactive format.
Your complete AI analyst repository (11 skills, 15 agents)
A working system. You get a configured CLAUDE.md that turns Claude Code into your analyst, 11 skills for visualization, data quality, question framing, and more, 15 agents for analytics, storytelling, validation, and presentations, connected data sources, and at least one completed analysis with charts and narrative. All markdown files you can read
8 hours of live instruction with 3 instructors
Saturday + Sunday, 4 hours each day. One instructor leads. Two troubleshoot and help you in real-time so nobody gets stuck. Every section is hands-on, you are building, not watching. Recordings of both days sent to all participants
Step-by-step guides for every section
Written companion guides so you can follow along at your own pace, revisit anything you missed, and reference setup steps later. Covers Claude Code installation, CLAUDE.md configuration, skill and agent creation with templates, data source connections, troubleshooting, and the complete build pattern.
Future bootcamp access (1 refresher cohort)
Material improves. Your registration includes access to join one future cohort of this bootcamp at no additional cost. Retake the bootcamp after a few months of using the tools, catch repo updates, and level up again.
Full course discount (your bootcamp price subtracted)
Your bootcamp investment applies directly toward the full AI Analytics for Builders course. The bootcamp builds the tools. The course teaches the analytical thinking (question framing, metrics, experimentation, storytelling) that makes those tools dramatically more effective.
Alumni community
Join a community of bootcamp alumni. Ask questions, share findings, get help troubleshooting, and see how others are using their AI analyst repos at their companies. Stay connected as the tools and techniques evolve.
Maven Guarantee
This course is backed by the Maven Guarantee. Students are eligible for a full refund up until the halfway point of the course.
Course syllabus
Week 1
Mar
28
Bootcamp Day 1
Lesson 1: AI Analyst Demo
Lesson 2: Set Up Claude Code
Lesson 3: Orientation - How the System Works
Lesson 4: The Build Pattern
Lesson 5: Build Your First Skill and Agent
Mar
29
Bootcamp Day 2
Lesson 6: Analyzing Data with your Agents
Lesson 7: Iterate and Improve the Agentic Data Team
Lesson 8: Analyze External Public Datasets
Lesson 9: Analyze Your Own Company Data
Lesson 10: Wrap-up
Schedule
Live sessions
8 hrs
Sat, Mar 28
3:00 PM—7:00 PM (UTC)
Sun, Mar 29
3:00 PM—7:00 PM (UTC)
Frequently asked questions
$600
USD