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.
A harness includes everything surrounding the model—such as the system prompt, tools, memory, skills, and subagents. Traditionally, this setup is designed once and remains unchanged for every task the agent performs.
Harness² introduces adaptability, enabling the agent to independently tailor its setup for each task while keeping model weights static.
With this approach, the agent proposes changes to its harness, tests multiple configurations, and refines it based on performance insights from those trials.
Because it learns from run-to-run variations, there's no need for a defined correct answer or an external grader to assess results.
This process isn't limited to single tasks. Harness² also transfers learnings across tasks.
Once a task is complete, the agent retains the optimized harness and the recurring insights from those runs. When working on a new task, it builds on this accumulated knowledge rather than starting over.
This continuous refinement enhances future task performance.
In trials with Gemini 3.5 Flash and GLM-5 on legal, office, and professional benchmarks, Google found that even one round of edits surpassed the performance of fixed harnesses, with further iterations driving additional improvement.
This points to self-healing, self-growing harnesses... 🤯
Agents improving their own setup is very cool . How do you prevent them from making changes that can make things worse?
Rewriting its own harness between runs without a grader telling it what correct looks like is the part I find hard to believe, so I want to see whether the accumulated experience actually transfers between unrelated tasks.
About Harness² on Product Hunt
“Harness the agent. Then harness its self-improvement.”
Harness² launched on Product Hunt on October 20th, 2026 and earned 156 upvotes and 5 comments, earning #3 Product of the Day. 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.
Harness² was featured in Open Source (69k followers), Developer Tools (521.5k followers), Artificial Intelligence (481.5k followers) and GitHub (41.4k followers) on Product Hunt. Together, these topics include over 268.9k products, making this a competitive space to launch in.
Who hunted Harness²?
Harness² was hunted by Chris Messina. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Harness² stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Chris Messina
A harness includes everything surrounding the model—such as the system prompt, tools, memory, skills, and subagents. Traditionally, this setup is designed once and remains unchanged for every task the agent performs.
Harness² introduces adaptability, enabling the agent to independently tailor its setup for each task while keeping model weights static.
With this approach, the agent proposes changes to its harness, tests multiple configurations, and refines it based on performance insights from those trials.
Because it learns from run-to-run variations, there's no need for a defined correct answer or an external grader to assess results.
This process isn't limited to single tasks. Harness² also transfers learnings across tasks.
Once a task is complete, the agent retains the optimized harness and the recurring insights from those runs. When working on a new task, it builds on this accumulated knowledge rather than starting over.
This continuous refinement enhances future task performance.
In trials with Gemini 3.5 Flash and GLM-5 on legal, office, and professional benchmarks, Google found that even one round of edits surpassed the performance of fixed harnesses, with further iterations driving additional improvement.
This points to self-healing, self-growing harnesses... 🤯