Below you will find pages that utilize the taxonomy term “Llm-Evals”
Technical Posts
Coordinator Prompt Design and Eval-Driven Verification (divvy-forge Part 3)
How I designed the coordinator and subagent prompts for divvy-forge as versioned markdown files, embedded subagent instructions inline, defined strict output contracts, and used promptfoo evals to catch three real prompt bugs before a single live agent run.
read more