Use the LLM Once. Then Never Again.

Mon, 18 May 2026 08:00:00 -0400

When you build with Claude, the default move is to put the model in the request path. User clicks a button, server calls the API, response goes back. It feels modern. It also makes every click cost money, take seconds, and produce a subtly different answer each time.

There’s a quieter pattern that works better for a lot of the AI work we’ve shipped: call Claude once during development, bake the answer into a JSON file checked into the repo, and at runtime do nothing but a dictionary lookup. The model isn’t in the path. It’s in the build.

Compliance Automation on AI Governance, HITRUST, and ONC Support

Use the LLM Once. Then Never Again.