Free Live Webinar Series

Text-to-SQL on Databricks Without the Model Bill

A live-build series from the creator of the open-source db-agent. No slides — real code, real failures, real fixes. One registration covers the series.

Next session

Text-to-SQL on Databricks Without the Model Bill

Run db-agent against a Databricks SQL warehouse using a free local LLM. Live demo.

Monday, October 12 · 5:00 – 6:00 PM EDT

Reserve your free seat

Microsoft Teams link sent instantly. Replay + the session notebook sent to all registrants.

Free · No credit card · Teams link sent instantly

Monday, October 12 · 5:00 – 6:00 PM EDT
45–60 min · live build + Q&A
Free · notebook included
What you'll see live
db-agent answering questions on a Databricks SQL warehouse
The LLM running locally through Ollama, with no API key and no tokens billed
The SELECT-only safety layer blocking a destructive query
What a local model gets right, and where it still gets the SQL wrong
C

Chandan Kumar

Founder, beCloudReady · Databricks Partner · Creator of open-source db-agent (AAAI-25 workshop demo) · Organizer, TorontoAI (10K+ members)

The problem

Every plain-English question to Genie or a frontier model API is an LLM call that is, or soon will be, billed by usage.

Genie One and Genie Agents are free for users only until January 31, 2027. Genie Code is already billed once users pass their monthly free allowance.

Many teams cannot send schema or data to an external model at all.

The series

Each session is built from features actually shipped in db-agent — and the failures found shipping them. Register once; we'll notify you as each session goes live.

01Text-to-SQL on Databricks without the model bill: db-agent with a free local LLMNext session
02Fully on Databricks: Lakebase as database and vector store, redaction-first agent memory via pgvectorComing up
03AWS S3 Vectors as an alternative shared memory store, for teams off DatabricksComing up
04The silent embedding bug that broke cross-agent memoryComing up
05Knowledge files: why schema alone makes agents hallucinateComing up
06What Databricks teaches vs. what we shipped — Genie, compared honestlyComing up

Who this series is for

Data & analytics engineers

You've built or evaluated a text-to-SQL agent and hit the wall every demo hides: real warehouses, real security zones, real business vocabulary the schema doesn't carry.

Data platform engineers

You run the Databricks workspace and many teams cannot send schema or data to an external model. This session shows text-to-SQL with the model running locally and the agent limited to SELECT.

Engineers building on db-agent

You found the repo (probably via Google). These sessions are the maintainer walking through shipped features, starting with local LLMs through Ollama and the SELECT-only safety layer, with the reasoning behind each.

Data team leads evaluating AI access to the warehouse

You need to know what production agents actually break on before committing a team to one. Every session is built from shipped open-source code and real failures, not vendor decks.

#1 on Google for “db agent”AAAI-25 Workshop ProjectOpen Source on GitHubDatabricks Registered Partner

Can't make it live?

Register anyway — every registrant gets the replay and the session notebook within 24 hours.

Register free — takes 10 seconds