We took a number off our homepage this week because it didn’t hold up on real code. If DebugAI ever wasted your time, we’re sorry. We’re making it better every day and shipping every week. Tell us what it gets wrong. We read every reply.
We make DebugAI, a VS Code extension: when a command fails, you run "DebugAI: Analyze Terminal Error" and it points to the line that broke, even when that line is in a different file from the crash. 2.14.0 is out now with a quieter first run: one sign-in, no surprise tabs, and on Windows the walkthrough no longer tells you to right-click in the terminal, which pastes whatever is on your clipboard straight into PowerShell. https://t.co/KRydvhrHv7
Send the same error again and the new answer is written with the last one in front of it. Send it twice by accident and you get one answer.
It runs on our side, so it already works in whatever version you have.
Now the error itself is the key. A repeat gets a new answer, written with the last one in front of it. A double send within 2 s gets one answer for one debug.
It runs on our side, so it already works in whatever version you have.
POV: you're building with ChatGPT.
Copy. Paste. Error. Repeat.
I built DebugAI to break the loop: it explains what broke, asks only for the lines it needs, and remembers the fix that worked.
Same error, new chat: the fix is back in seconds.
Coming soon to ChatGPT and Codex.
Lab notes #001. Our founder spent four weeks finding out why bugs our AI agents fixed kept coming back, then built a checker that now guards our own code. Here is what it found, the misses included. Every number from here on gets published the same way.
I spent four weeks making Claude Code read our entire codebase to find out why fixed bugs kept coming back. Then I started building something to fix it. Here are the first two runs, including the number that hurt. https://t.co/WHe7GWSFJk
Every dev has a number they've never seen...
I'm building something at @debugai_x that shows you yours. No one's done this in dev space yet; devs are gonna love it...
comment your guess or RT n I'll count you in for early access.
@debugai_x For the ones who'd rather decode them: the same three as equations. Every line in this video is drawn by the equation printed under its figure. Follow @debugai_x for the reveal this weekend.
@debugai_x For the ones who'd rather decode them: the same three as equations. Every line in this video is drawn by the equation printed under its figure. Follow @debugai_x for the reveal this weekend.
The engine moved to Claude Haiku 5.5 on 10 Oct. We ran it on 12 real bugs from our own history before switching. The numbers are in the post, including one fix it now gets wrong.
Agents: npx -y @debugai/mcp setup
https://t.co/Noh92ndECS
DebugAI 2.12 is out.
From 2.10 to 2.11, "Index Entire Workspace" indexed zero files, so answers only knew the files you'd happened to open. That's fixed, and a debug now sends less from your machine.
Update, then run Index Entire Workspace once.
What a debug stops sending in 2.12:
- your git diff, branch name and changed file paths. Our API never read any of it.
- code from a focused .env, key or credential file. The error still goes, and the status bar says what was held back.
Embarrassing one: our "Index Entire Workspace" indexed zero files since 2.10, so answers only saw what you'd opened.
2.12 fixes it, so debugs use your whole project again. It also stops sending your git diff (we never used it), and the engine's on Claude Haiku 5.5.
Out today.