How we made evals 100× cheaper with multi-agent architecture
Comments
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Summary
Cleric, an AI investigation agent for system alerts, split its single monolithic agent into a team of roughly 40 specialized agents, each run on its own model and harness.