# Google Releases Harness2 for AI Agent Self-Improvement

> Google's Harness2 lets AI agents rewrite their own playbook without model changes.
- Title: Google Releases Harness2 for AI Agent Self-Improvement
- Summary: Google's Harness2 lets AI agents rewrite their own playbook without model changes. Google open-sources Harness2, an AI framework that enables agents to…
- Keywords: google, harness2, ai agents, self-improvement, propose probe compose, workbench, jobbench, lab benchmark, tomas pfister, google cloud ai research, startups, business
- Source: Startup Fortune — https://startupfortune.com/google-open-sources-harness2-letting-ai-agents-rewrite-their-own-playbook
- Published: 2026-10-18T13:30:08+00:00
- Read time: 1 min
- Topics: google, harness2, ai agents, self-improvement, propose probe compose, workbench, jobbench, lab benchmark, tomas pfister, google cloud ai research, startups, business
## Google Cloud AI Research releases Harness2
Google Cloud AI Research released Harness2 on October 9 under an Apache 2.0 license to let AI agents rewrite their own scaffolding without manual patches.
## Harness2 doesn't change model weights
Harness2 keeps model weights frozen while editing instructions, tools, memory, and routines that decide agent actions.
## Propose-Probe-Compose mechanism
The Propose-Probe-Compose framework proposes two edits, probes them, and composes changes based on observed behavioral contrast without labeled correctness.
## Performance gains on benchmarks
Harness2 added 11.5 points on WorkBuddy-Bench, 4.5 points on JobBench, and 11.8 percentage points on LAB before recursion.
## Claude Opus as editor model
Google used Claude Opus 4.8 to propose and compose harness changes, a detail highlighting Anthropic's role in the framework.
## Self-improvement debate intensifies
Harness2 makes harness engineering the most plausible near-term path for agent self-improvement, shifting focus from model weight updates.
## Limitations of self-improvement
Systems often stall after one structural fix due to lack of internal model for why changes worked, leading to reward hacking without compounding gains.
## Key takeaway

Google open-sources Harness2, an AI framework that enables agents to self-improve by editing their own scaffolding without altering model weights.