Ali Johnson's profile on Product Hunt

About

Hey Hunters! 👋 fixRAgent is a visual intelligence engine for your physical assets. As an industrial manufacturer & real estate investor, I learned the hidden tax of property ownership is the mental load. Where is the manual? What’s the exact SKU for this mower blade? Generic AI hallucinates mechanical advice. I wanted precision. I built a computer vision pipeline that identifies model plates and hardware to instantly provide: ⚙️ Verified SKUs: Maps visuals to exact replacement parts with direct buy-links. 📚 Instant Manuals: Pulls exact OEM manuals and schematics for your specific model. 🛠️ Dynamic SOPs: Generates step-by-step operating and repair procedures. It’s a digital twin for your home, garage, and rentals. Scan the Problem. Own the Fix.

Links

fixRAgent

Facebook

Badges

Tastemaker

Gone streaking

Forums

p/open-wearables

•

5h ago

Why does your recovery score say 58% today?

I wear a WHOOP. I've coached people on movement and sleep for many years and I still can't answer that question for myself. The algorithm is locked. You get a number, you trust it, you stop there.

When we built Open Wearables, we decided the scoring layer should work differently. Sleep Score and Resilience Score shipped in v0.5 - every coefficient, every threshold, every weighting is in the repo and you can fork them, tune for endurance athletes or elder care or clinical populations. Moreover, you run them on your own infrastructure and the same algorithms feed the MCP layer so AI coaching can cite the actual data behind a recommendation instead of approximating.

•

6h ago

We benchmarked Claude Code refactoring, with and without code health guidance

We ran a benchmark to see how well @Claude Code actually refactors legacy code alone and then redid the same test, but this time with code-health guidance via MCP server.

To limit any vendor bias, we used a public data set of 25,000 source code files from competitive programming, including carefully crafted unit tests.
We assessed agent correctness by running those tests.
We measured the Code Health impact using CodeScene.
(See our research Code for Machines, Not just Humans for more details on the methodology and data)

Claude Code that was MCP-guided achieved 2 5x more more improvements in Code Health compared to unguided refactoring.

•

19h ago

fixRAgent - Scan the Problem. Own the Fix.

fixRAgent is a visual intelligence engine for physical assets. Stop guessing at the hardware store or losing manuals. Snap a photo of any appliance, mower, or mechanical failure. Our custom computer vision instantly identifies the exact model to pull verified OEM manuals, map visual components to exact replacement SKUs, and generate dynamic, step-by-step repair and operating SOPs. It’s a digital twin and master-manual for your home, garage, or rentals. Scan the problem. Own the fix.