A separate evaluator agent is what makes long agent runs worth the money

Mon, 05 Oct 2026 17:00:00 +0000

Ask one agent to build a whole application and two things tend to go wrong. It loses the thread as its context fills, and it grades its own work generously. Anthropic’s engineering team wrote up a harness design for long-running application development that attacks both, and the numbers are honest about what it costs.

Evaluation on Tokenise

A separate evaluator agent is what makes long agent runs worth the money