
Harness²
Harness the agent. Then harness its self-improvement.

Harness² from Google Research is a plug-and-play recursive agent harnessing framework that lets LLM agents automatically evolve their execution harnesses (prompts, tools, memory) for open-world tasks—without ground-truth verifiers. Dual recursion: task-level Propose-Probe-Compose refinement + harnessing-level accumulation of reusable experience. Up to +11.5 points on professional benchmarks like WorkBuddy-Bench.
AI Analysis
AI analysis not yet available for this product.
Similar Products

Cohere Parse 5
Turn complex docs, tables & images into AI-ready data
▲ 158 votes

Adapt
The company brain that gets work done
▲ 124 votes

Replay QA Security Scan
Automated Penetration Testing for AI-Built Apps
▲ 102 votes

WikiFix for Confluence
Find and fix issues in your knowledge base
▲ 86 votes

Audryo
Customer email your agent can operate.
▲ 68 votes
Refoid
Automate App Store refund responses and track every outcome
▲ 68 votes