Company brain
Build your company brain on your warehouse
Rig keeps your company’s data in tables in your warehouse, and Rig Map records what each table means. Claude, your agents and your team answer from the same numbers.
What’s our net revenue retention for enterprise accounts last quarter?
Used Rig integration
search_metricsnet_revenue_retentionget_metric_detailscustomer × quarterexecute_sql1 row returnedNRR for enterprise in 2025 Q4 was 112%.
Resolves to your certified net_revenue_retention metric, filtered to segment = 'enterprise' for period = '2025Q4'. Rows scoped per RBAC.
Notes and documents make a poor store for company numbers
Teams build AI brains from markdown files, Notion pages and document search because they are quick to write. Ask one for revenue by segment last quarter and it reads whatever text it finds, so two people get two answers.
What the brain is made of
Markdown files
Tables in your warehouse
Customers, deals, tickets and invoices sit in rows and columns, so a question gets the same answer every time someone asks it.
Context in long prompts
Rig Map
Rig Map records what each table and column means, how tables join and which metric is certified, and updates as schemas change.
An MCP for every tool
One MCP connection
Claude and other agents reach every system through Rig’s MCP access, with each person’s or agent’s permissions applied.
Definitions that drift
Certified metrics
The people who own ARR, churn and pipeline define each one once and review it.
Unwritten rules
Usage rules
Your team writes down edge cases, such as which deals need CFO sign-off, and answers follow them.
Answers you cannot check
Answers you can trace
Every answer shows the metric and the query behind it.
How the work runs
Bring the data in
Ingest syncs your tools into a warehouse, or Rig works on your existing warehouse.
Map it
Rig drafts table descriptions, joins and metrics from the warehouse, and your team reviews and certifies them.
Write down the rules
Each team records the definitions and exceptions it already works to.
Connect your tools
Claude, Cursor, Slack and your own agents connect through Rig.
Where to start
Common questions
Is a company brain a knowledge base?
Rig’s is not. Handbooks and training documents suit a file store, and Rig holds the numbers: data in tables, read with SQL, with a map that tells AI what each table means.
Which AI tools can use it?
Claude, Claude Code, Cursor, Codex and ChatGPT connect through Rig’s MCP access, and so do agents your team builds.
How does it stay current?
Rig Map rereads your warehouse whenever a schema changes, and your team reviews the new definitions.
Who decides which numbers are right?
The people who own each number decide. Finance certifies revenue and sales certifies pipeline, while the data team manages access.
Do we need to move our data?
No. Rig works on Snowflake, BigQuery, Redshift or Postgres, or on a warehouse we host for you.
Talk to Rig
What work do you want to improve?
Tell us where your team spends time, loses money or needs better information.
In a 30-minute call, we’ll discuss the data and systems work that could help.