Learn Count
Count is a platform for analytics and research, built for work you can’t afford to get wrong.
Your team and Count’s agents work together on one shared canvas. Every answer is laid out as a Reasoning Chain showing its sources, assumptions and inferences, and you can see everything your agents do.
These docs cover how to set up, work in and govern Count. For more on why we built it this way, read our blog.
Hallucinations Are a Big Problem
Topics
Reasoning ChainsNew
AI answers you can trust. Reasoning Chains trace every claim back to the data, sources and assumptions behind it, so you can see exactly how the agent got there.
Start Here
Count is a place to analyse data and do deep research into any topic, together with your team. Getting going is simple.
Data Sources
Gather all your business knowledge in one place.
Working in The Canvas
Learn more about how working in and with the Count canvas, from the agent and canvas objects to team collaboration and shareable reports.
Build Trusted Context
Manage the skills, context and definitions across your organization.
Integrating Count
Learn more about how to connect Count to other tools, from using it in agentic tools like Claude or Cursor, to controlling it programmatically via the API, to bringing it into Slack.
Managing Your Workspace
Learn more about Count's permissions, telemetry and, security and governance controls.
Analytics Engine
The compute layer behind Count's agents: cells, Python, and an in-memory engine that keeps analysis fast and warehouse costs low.
