Build a Text-to-SQL AI Agent on Databricks — 2-Hr Hands-On Bootcamp
In 2 hours, build and deploy a production-style text-to-SQL AI agent on Databricks — with SQL safety guardrails, schema-aware prompts, and live deployment. Only 20 seats.
What You'll Build
A working AI agent that converts natural language into safe SQL, validates it against schema and SELECT-only guardrails, executes on Databricks, and returns results with explanations. You leave with a repo you can deploy at work Monday.
Why This Bootcamp Exists
80% of new enterprise databases are now generated by AI agents (Databricks 2026 State of AI Agents). Every data team is being asked to build one. Most get the LLM call right and the safety layer wrong. This session fixes that.
You'll Leave With
A deployed text-to-SQL agent on Databricks (your own workspace or ours)
The open-source db-agent repo cloned and configured
A working SQL safety validator (SELECT-only, schema-enforced)
The full prompt engineering pattern for schema-aware generation
Deploy-ready patterns for Streamlit, FastAPI + Next.js, and AWS Lambda
Who It's For
Data Engineers and Analysts who want to ship internal AI tools fast
AI / Platform Engineers building agentic workflows over production data
Technical leads evaluating text-to-SQL for their teams
Prerequisites
Comfort with Python and SQL. A laptop. A GitHub account. That's it.
About Your Instructor
Chandan Kumar
Founder of BeCloudReady (Databricks Registered Partner)
Organizer of TorontoAI (10K+ members).
Author of the open-source db-agent project (github.com/db-agent/db-agent), presented at the AAAI-25 workshop on AI agents.
Format
Live on Microsoft Teams.
Recording sent to attendees within 48 hours.
Saturday, May 16 — 12:00-2:00 PM EDT.
Capped at 20 seats.
Build something real. Not just prompts.
URLs