Natural-language Analytics

Data Sensei

Chat with your data sources in plain English.

Data Sensei is a natural-language analytics product that lets your team query connected data sources — Metabase, PostgreSQL, Mixpanel, and Google Analytics — by chatting in plain English. Build governed pipelines, ask questions from Slack, and get answers grounded in your own warehouse using whichever LLM you have configured.

Get AccessBack to platform
Capabilities

What Data Sensei does

Bring your own data sources

Connect Metabase, PostgreSQL, Mixpanel, or Google Analytics with your own credentials, encrypted with AES-256-GCM at rest.

Governed pipelines

Pipelines wrap data sources with the schema, joins, and metric definitions you want the AI to use. The AI never queries arbitrary tables.

Natural-language chat

Ask questions like "what was last week's WAU by source?". Data Sensei translates the prompt, runs the query against your warehouse, and returns a grounded answer with the SQL it ran.

Slack integration

Pipe any pipeline into Slack. Mention the bot in a channel, get an answer threaded back in seconds.

Per-pipeline LLM config

Choose Anthropic or OpenAI per pipeline. Tune temperature, model, and context-window per use case.

Audit trail

Every chat, prompt, and generated query is logged in your own database so analysts and auditors can replay any session.

Integrations & data sources

  • Metabase
  • PostgreSQL
  • Mixpanel
  • Google Analytics
  • Slack
  • Custom data sources via adapters

On the stack

  • PostgreSQL 16 + pgvector
  • Knex.js
  • Anthropic Claude / OpenAI
  • BullMQ
  • Socket.io
Data Sensei FAQ

Data Sensei — common questions

Data Sensei is a natural-language analytics product. It connects to your data sources (Metabase, Postgres, Mixpanel, Google Analytics), wraps them in governed pipelines, and lets your team ask questions in plain English from the dashboard or from Slack.

Ready to run Data Sensei on your infrastructure?

Get early access to the full Juniors workspace.

Get Access