The community building agentic analytics.
Agentic analytics is AI agents that answer data questions in plain English. Join the open community learning to build ones your whole company can trust.
A community you can actually meet.
Meetups in New York, Paris, and Berlin, hackathons in Paris, and a lot of open laptops. Hover an event, then click to open the gallery.
We want analytics agents teams can actually trust
So we are building them in the open, together.
Read the manifestoFour ways in.
Learn
12 short lessons, from first principles to a deployed agent. Free, in order, at your pace. Plus a 14-term glossary.
Follow the path →Compare
19 tools, side by side, no vendor spin. Pick any two and see exactly how they differ.
Open the tool →Events
Meetups, workshops, and conferences from across the data world, online and in person. Come say hi.
See what's on →Publications
Guides, benchmarks, and opinion on agentic analytics from people doing the work.
Read the latest →Upcoming events
All events →Latest publications
All publications →- GuidesIs read-only MCP access to your database safe?Read-only database access sounds safe for an AI agent, but a real SQL-injection flaw in a popular MCP server bypassed it. Why it is not enough, and what is.
- GuidesWhat is agentic analytics?Agentic analytics is AI agents that answer data questions in plain English by writing their own queries. How it works, why it is hard, what makes one reliable.
- GuidesText-to-SQL vs the semantic layerText-to-SQL writes queries on the fly, a semantic layer serves predefined metrics. How they differ, what the benchmarks show, and when to use each in an agent.
The Agentic Analytics Playbook
A practical guide to shipping analytics agents that last. How to scope it, choose your tools, build the context, roll it out, and measure it.
Get the playbook →Come build this with us.
One email when something in agentic analytics actually matters, plus an invite to the next event. No spam, no hype, unsubscribe any time.