Making Tools Discoverable
AI for AI: using models to predict how other models will search.
All Authors
Chris Sachs
Page 2 of 3
A Universal API Bridge
The milestone where success became a possible outcome.
When There's Nothing to Embed
RAG assumes documents exist. For tool discovery, they don't—until you create them.
TypeScript Types for LLM Tools
LLMs understand TypeScript better than JSON Schema. Here's how we exploit that for better API execution.
Tools as Data, Not Code
Why retrieval-based AI tool use requires treating tools as data, not code—and what that makes possible.
The Future of Tool Use
Where AI agents are heading—and the infrastructure they'll need to get there.
Isolating Credentials
Most API specs model authentication as parameters instead of security schemes. We transform them so credentials stay out of LLM context.
The Case for Broken Standards
JSON Schema is a mess. OpenAPI is poorly designed. But the value of a standard isn't its elegance—it's its existence.
Spec-Driven Execution
How we collapsed OpenAPI's encoding complexity into composable primitives.
Interface Synthesis
How we bridge the gap between what LLMs generate and what APIs require.