👋 CEO @ContextBridgeAI, @PatchWaveAI Former LinkedIn, Homebound, GuildEducation, Bizo, etc. Remote Cameron Crazy (Go Duke!)
Denver, CO
Joined May 2007
- Tweets2.8K
- Following1.3K
- Followers676
- Likes8.7K
Hey @chromaticcom please stop spamming me. I tried to login an opt-out but it isn't obvious where to do that. So I guess I'll try it here.
Just had an agent "proaccidentally" open an issue on a open source project on my behalf. Super annoying!
Loco loco.rs/ takes the Rails concepts and carefully adapts them to idiomatic Rust. Curious if anyone has thrown a clanker at porting a Rails repo to Loco?
My company owns the domain slopportunitycost.com what should I do with it?
🧟🎃 Halloween is coming up. Is anyone thinking about a themed launch of a product? Last time I did that it was with an experimental (now defunct) JVM LiveView library called Undead. github.com/floodfx/undead
No one ever got promoted for landing Dependabot PRs or any other software maintenance for that matter.
"I’m considering whether I need to read the plan I wrote. I thought maybe I don’t need to"
-- GPT 5.5 in a reasoning trace
🤣
even the AI doesn't want to read AI generated text!
#clankerfail
If you've ever settled for a less than ideal plan from a coding agent because iterating in a terminal sucks you should try PlanBridge: plan.contextbridge.ai
Your CLAUDE.md used to be accurate. 200 PRs later? It's full of legacy instructions. And your agent is a confused slop-machine.
ContextBot does more than read PR comments. It learns from the code you merge every week. The diff itself carries signal about how your team writes code. That's where the implicit patterns live.
ContextBot is free during our public beta. Install the GitHub App and get your first context-improvement PR in minutes.
ContextBot stops the context rot.
contextbridge.ai/blog/contex…
Two studies tested AI context files.
One found they decreased success rates by 3%.
The other found they improved pass rates from 53% to 100%.
Both are right. Here's why:
Quick audit for your CLAUDE.md or AGENTS.md:
For every line, ask: if I deleted this, would the agent behave differently?
If not, that line is just burning tokens.
We broke down both studies and built a practical framework for context files that actually improve outcomes.
contextbridge.ai/blog/your-a…
