Talk

Agent Harness Optimization Workflow

From Wikiprompt, the free prompt encyclopedia

codila
Contributed bycodilaXSource

Oct 3, 2026

Agent Harness Optimization Workflow A step-by-step workflow to reduce agent harness costs by 50%+ using Karpathy's loop, action fusion, context compaction, output archiving, and model delegation.

Prompt ContentSave

🌐
step 1 β†’ inspect the agent's execution logs - repeated actions, growing context, oversized outputs - find where tokens stop moving the task forward step 2 β†’ run Karpathy's loop on the harness: propose β†’ implement β†’ review β†’ test β†’ keep or discard. Fix the quality and efficiency gates before the search starts step 3 β†’ fuse actions: edit the file and run its planned test in one tool call - remove the model round trip between them step 4 β†’ compact at completed steps - but only when expected savings outweigh the cost of rewriting the cached context step 5 β†’ stop replaying huge outputs: archive them, send them twice, then keep a handle and short excerpt. Retrieve exact pages when needed step 6 β†’ delegate log reading to a cheaper model - verify its evidence against the original. If verification fails, return the full log step 7 β†’ start with one mechanism in Pi, where their code runs. Measure it against your current setup before combining all four step 8 β†’ freeze the changes, then test on unseen tasks. Track completion, API cost and tokens together - a cheaper failure is still a failure

Sign in to see the full prompt

Continue with:

By logging in, you agree to our Terms of Use and Privacy Policy

Usage

This prompt is designed for use with productivity. Copy the prompt content above and paste it into your preferred AI tool.

For best results, you may customize the placeholders (indicated by square brackets or capital letters) with your specific requirements.

References

Categories:productivity| twitter| agent-harness| cost-optimization

Talk