Show HN: Automated bug fixing powered by LLMs
resolvd.aiHey everyone,
My friend and I built a simple bug fixing app that listens for alerts/issues from Sentry, contextualizes it against your codebase, and any other data sources you wish to connect (right now we support Notion, Google Docs, and Slack), and deploys an ai agent to write a PR for review in Github or Gitlab to solve the bug.
Our current demo shows the end-to-end process for a trivial bug fix, but we have been testing it with open source python repos like http-pie, comparing how our agent solves a bug compared to a human engineer and it gets fairly close. We are working on adding unit tests for any bug we fix to make sure the code is actually merge worthy.
The goal is to remove monotonous/low-level ticket work for SREs/Devs at startups/smaller companies pushing fast, eventually scaling to help gather context and solve more complex bugs.
Lots of ideas of where to go from here! Let me know if you have feedback and you find this useful :)
If you want access/use sentry I'm happy to onboard the first 10-15 people that want access today! Want to start slow bc I'm not sure what scale it can handle just yet. Just fill out the 'Get Started' form and I'll email you access, so far two of our friends companies are using it and like it.
Thanks! I can see how this can save time with low severity incidents at places i've worked. Great use-case for LLMs. Have you had any feedback so far?