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, SQL databases, 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

01

Bring your own data sources

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

02

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.

03

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.

04

Slack integration

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

05

Per-pipeline LLM config

Choose any supported LLM provider per pipeline. Tune temperature, model, and context-window per use case.

06

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
  • SQL databases
  • Mixpanel
  • Google Analytics
  • Slack
  • Custom data sources via adapters

On the stack

  • Your own database
  • Governed pipeline contracts
  • Any LLM
  • Background workers
  • Real-time chat streaming
MCP + API

Drive Data Sensei from your AI agent

Data Sensei is exposed through the Juniors AI MCP server, so Cursor, Claude, and any other MCP client can work with it directly. Grant a key the data-sensei:read scope for the read tools, or data-sensei:write to include the writes.

Read3 toolsdata-sensei:read
  • data_sensei_list_sources

    Every connected data source (Metabase, Postgres, Mixpanel, Google Analytics).

  • data_sensei_list_chats

    The data chats the calling key can see.

  • data_sensei_get_chat

    One chat with its full message history and the SQL each answer ran.

Write2 toolsdata-sensei:write
  • data_sensei_create_chat

    Open a new chat against a governed source or pipeline.

  • data_sensei_send_message

    Ask a question in plain English and get a grounded answer back.

Try asking your agent

“Open a chat on my Postgres source, ask for weekly active users over the last 8 weeks, and show me the SQL you ran.”

Set up MCP

33 tools across all six products, plus a public OpenAPI spec at /api/openapi.json if you would rather call the REST API directly.

Data Sensei FAQ

Data Sensei - common questions

Data Sensei is a natural-language analytics product. It connects to your data sources (Metabase, SQL databases, 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 AI workspace.

Get Access