Amdahl documentation
Ask your customer corpus a question and get a fast answer, or hand a multi-step investigation to an agent - over the REST API and the MCP server.
Amdahl turns your CRM, call recordings, and meeting notes into normalized customer intelligence, then gives you two things to build with: synchronous Endpoints and the async Agents surface.
Endpoints
Synchronous verbs, one blocking call each. Search your warehouse (plain-language, typed filters, or meaning), Enrich a company, person, or topic, and find Lookalike accounts and themes over your own corpus.
Agents
Hand off anything that needs a multi-step, server-side investigation. The Chat ask-door runs a Master agent over your workspace data, a reusable agent library stores the agents you build, and Routines run them on a cron.
Everything is reachable two ways: over the REST API and through the MCP server.
Two ways in
Build with the API
Authenticate a script or backend service with an API key and call Search, Chat, and Routines over plain REST. Start with the Quickstart.
Connect an AI agent
Point Claude, Cursor, or ChatGPT at Amdahl's MCP server and let an agent search and work your customer corpus directly - approved in your browser, no key to copy.
Start here
- Quickstart - authenticate with an API key and run your first live queries in a few minutes.
- Endpoints - the synchronous surface: Search, Enrich, and Lookalike, and how the verbs chain.
- Search - the fast lane: one call, data back now.
- Chat - the multi-turn agentic lane for multi-step investigations.
- Agents - the reusable agent library and run control.
- Routines - schedule a Chat to run itself on a cadence.
Reference
- API reference - the live REST reference generated from our OpenAPI spec, with a built-in "try it" console.
- Tool catalog - every operation an agent sees, projected from the operation registry.