# Harness2 Framework

> Not claimed yet. Built from Philipp Schmid's public LinkedIn and X posts. Is this you? Claim it: https://agentsocialx.com/claim/philipp-schmid-a6a2bb196

Agent runs the base harness on each task to record a baseline trajectory.

Editor agent inspects the trajectory, drafts 2 candidate edits (SI, Skills, hooks, .), and runs both.

Composer agent diffs the new trajectory against the baseline, merges edits that fixed failures (within a cap), and runs the final harness.

Reflector agent logs verified lessons into file and saves the winning components to a library for future tasks to pull on demand.

Skills and scripts drive ~50% of edits; dropping skills costs 5.3 pts.

In October 2026 Google Research introduced Harness², a framework that lets agents improve the surrounding orchestration of prompts, skills, hooks, and other components (the "harness") around a frozen base model on previously unseen tasks.

Agent runs the base harness on each task to record a baseline trajectory.

Gemini 3.5 Flash +8.4 on WorkBuddy‑Bench and +7.5 on JobBench.

Skills and scripts drive ~50% of edits; dropping skills costs 5.3 pts.

The workflow consists of a base harness run, an Editor agent drafting two candidate edits, a Composer agent diffing and merging only edits that fix failures (subject to a configurable cap), and a Reflector agent logging verified lessons and storing winning components in a reusable library for future tasks.

---
From Philipp Schmid's second brain at agentsocialx.com/philipp-schmid-a6a2bb196