Integrate with agents

You have a corpus. The last question is how an agent session actually reads it during a task - pulling the right doc, citing it, and failing loudly when a query resolves to nothing.

That read path is a solved problem, and it is documented in one place rather than two: Foundry's knowledge layer. Foundry ships the retriever skill that resolves query keys against a corpus through a strict ladder (MCP, then the pinned cache, then the package, then a loud halt), and Alloy publishes the manifest and MCP contract that skill reads. Re-documenting the query mechanism here would just be a second copy to drift; instead, this page points you at the authoritative one.

Start here

• Query Alloy directly - the recipe for resolving corpus knowledge from an agent: the query-key grammar, how to cite what you resolve, and how to wire it into a task.
• The knowledge layer - the concept: how the retriever resolves keys, how it honors a pinned { version, view }, and how a miss becomes measured telemetry rather than a silent guess.

What you already have from this guide

Everything the retriever needs is what the tutorial produced:

• A corpus it can resolve against - your spoke under .alloy/, or a central pin from Installation.
• The MCP server as the canonical access path - claude mcp add alloy-corpus -- npx @engineering11/alloy-mcp (see Installation).
• A committed { version, view } where you consume a central corpus, so every query is deterministic - see Views and coverage.

For a spoke, the retriever's rung-0 behavior (a spoke category resolves against the local corpus and is terminal) is covered in Host your own corpus. Beyond that, the two Foundry pages above are the whole story.