The AI-native data stack

Build the whole stack,
from Claude Code.

Lakehouse, pipelines, semantic layer, dashboards — all provisioned from a single prompt in your agent. MCP-native, fully governed, shipped to production in minutes.

claude · ~/acme
~/acme-corp $
> Build me a sales pipeline dashboard. Connect to our Postgres database.
✓Connected to Postgres at db.acme.com:5432
✓Found schemas: public, analytics
✓Found tables: users, teams, events, integrations
✓Created semantic model with 23 metrics
✓Built dashboard: definite.app/d/sales-pipeline
§ 03 — Model Context Protocol

Your data,
in your agents.

Definite speaks MCP natively. Point Claude, Cursor, or any agent at your warehouse — they'll get schema, lineage, and semantic context automatically. No glue code, no scraping, no guesswork.

Schema & lineage
available to any MCP client
Row-level security
permissions travel with the data
Semantic layer
metrics defined once, used everywhere
Connected agents
Claude
Claude
ready · mcp://definite
live
ChatGPT
ChatGPT
ready · mcp://definite
live
◉
Cursor
ready · mcp://definite
live
◉
Custom agent
via SDK
live
§ Two ways in

Live in the terminal,
or in a browser.

Same power either way. Pick the surface you're already in.

01 · Fi · In the browser
Not into the CLI?

Fi is our web-based AI analyst. Same stack access, same governance, shipped through a chat UI built for your whole team.

Try Fi →
02 · CLI · In the terminal
Give me the skill.

Add Definite to Claude Code, Cursor, or any MCP client in 30 seconds. One API key, full stack access.

Read the docs →
§ Agent, meet governance

Fast to build.
Safe to trust.

The agent writes the queries. The platform keeps them honest — so your CFO can trust the numbers that land on their dashboard.

01
Semantic layer, not raw tables

Agents query defined metrics — consistent numbers across every dashboard, every time.

02
Row-level security, by default

Define who sees what once. Every query, export, and dashboard respects the rules.

03
Full audit trail

Every change tracked. Every query logged. Your CFO can trust what the agent built.

§ Metrics as code

Dashboards you can diff.

Your data stack lives in your repo, not a vendor's UI. Code-review KPIs. Deploy dashboards like you deploy code. The agent opens the PR; you approve the metric.

models/sales.yaml● on main
name: deals
sql_table: lake.hubspot.deals

measures:
  - name: total_revenue
    description: Total closed revenue in USD
    sql: amount
    type: sum

  - name: win_rate
    description: Percentage of deals marked as won
    sql: "COUNT(CASE WHEN status = 'won' THEN 1 END)::float / COUNT(*)"
    type: number

dimensions:
  - name: stage
    description: Current pipeline stage
    sql: stage
    type: string

  - name: closed_date
    description: Date the deal was closed
    sql: closed_at
    type: time

Your answer engine
is one afternoon away.

Book a 30-minute call. We'll build your first dashboard on the call — or you can stop paying us.