Harness Design for Long-Running Application Development
Source
Anthropic Engineering
Author
Anthropic Engineering
Date
Terms in this piece · Glossary
agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
context compaction — Summarizing an agent's earlier conversation to free room in the context window so a long session can keep going.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
If you're building agents for long autonomous coding sessions, this explains two concrete fixes worth adopting: resetting context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → instead of compacting it to avoid degraded coherence, and running a separate evaluator AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → to counter LLMs' tendency to over-praise their own generated work.
Key quotes
“Harness design is key to performance at the frontier of agentic coding.”
“Taking inspiration from Generative Adversarial Networks (GANs), I designed a multi-agent structure with a generator and evaluator agent.”
“The final result was a three-agent architecture—planner, generator, and evaluator—that produced rich full-stack applications over multi-hour autonomous coding sessions.”
“Whether a layout feels polished or generic is a judgment call, and agents reliably skew positive when grading their own work.”
“Separating the agent doing the work from the agent judging it proves to be a strong lever to address this issue.”
