What is Combined? Business data for the AI agents you already use
How Combined connects SaaS data, keeps it queryable, and gives external AI agents scoped access through SQL, MCP and SDKs.
THE COMBINED FIELD GUIDE
Practical tutorials, working examples and decisions worth getting right before your agent answers a business question.
How Combined connects SaaS data, keeps it queryable, and gives external AI agents scoped access through SQL, MCP and SDKs.
A practical setup guide: connect a source, grant access, add the MCP server, discover schemas and verify a real query receipt.
Turn HubSpot deals into answers in your AI workflow. Follow the connection steps, copy a pipeline-analysis prompt and check it against a simple worked example.
Choose the right path to business context: direct application tools for actions, or Combined for SQL over synced, permissioned business records.
Evaluate Combined for the whole path from business apps to agent answers: managed ingestion, storage, scoped MCP access, and $5 per million MAR after the trial.
Compare direct APIs, replication and managed agent data platforms. Use a practical checklist to evaluate source readiness, permissions, freshness and cost.
Use SQL for exact calculations over structured records and semantic retrieval for meaning in text. Work through a reproducible business-data example.
Define acceptable data age, distinguish a successful sync from complete coverage, and make agents disclose stale or missing sources.
Understand the query engine, table format and operational responsibilities behind a managed business-data layer for agents.
The role of forward deployed engineers in bringing AI systems into production.