Ali Johnson

Ali Johnson

fixRAgent: Photo triage for PMs and Devs
#97375306 followers17 following
✨ 3 day streak
#7,289Last month
1 KP
>10,000All time
4 KP

About

Hi, I'm Ali. Russ and I built fixRAgent. For property managers: tenants scan a QR sticker in their unit and send one photo. You get a Triage Profile: what it is, how urgent it is (Emergency, Today, This week, Whenever), which trade to call, and what to tell the tenant. You still decide who goes. For developers building property software: one API call gives you the same answer as data. A free key gives you 60 requests a day. It also works inside Claude, ChatGPT, Cursor and Gemini. By property managers, for property managers. Tell us where it's wrong.

Badges

Tastemaker
Tastemaker
Gone streaking
Gone streaking
Gone streaking 5
Gone streaking 5

Maker History

Forums

•

1mo ago

fixRAgent - Triage the photo. Route the fix.

Built for property managers and maintenance teams. One photo of a maintenance problem in: what it is, how urgent it is (Emergency, Today, This week, Whenever), which trade to call, and what to tell the resident. Residents scan a QR sticker. No app.
Open Wearablesp/open-wearables•

6mo 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.

•

6mo 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.

View more