HN Explorer

Show HN: FixBugs – Reproduce production bugs and verify fixes (fixbugs.ai)

43 points by kirtivr ↗ HN
I built FixBugs, an agent that ingests the rich context surrounding production bugs to reproduce them in a sandbox and generate verified fixes. It's available in the form of a self-hosted VSCode extension and as a Github app:

VSCode Extension: https://fixbugs.ai/go/vscode-extension

  - full code and data privacy.
  - zero data retention models opted out of training.
GitHub App: https://fixbugs.ai/go/github-app

  - we do access your code temporarily.
  - pick a repo to install FixBugs on.
What motivated me to build FixBugs were my years being on-call at Google and VMware. How many hours did I spend gathering logs, traces, reviewing metrics, and reading code only to find that,

* Some context was missing.

* The bug wasn't reproducible.

* The alert was caused by a transient infrastructure issue.

Too many. Inefficiency in investigating staging/production bugs has a real cost, and it's paid both by developers and customers.

Current capabilities:

  - Reproduce the bug.

  - Identify the root cause.

  - Generate a fix.

  - Verify the fix.

  - Review the generated code using multiple AI models to help catch potential regressions.
Do try it and let me know what you think!

I'd especially love feedback from engineers who work with distributed systems or handle high-volume production bug triage.

31 comments

[ 4.2 ms ] story [ 59.8 ms ] thread
kirtivr
A different approach that we took to root causing bugs that you may find interesting is that we first try to reproduce the bug before coming up with a fix for it.

This is essentially a (RCA <-> Repro test case) loop until we're recreated the bug. If our attempts are not converging and we’re on the wrong track, we ask for human input.

yizluo
very nice tool! helpful and I love it
raghu16
Also, How is the VSCode extension reproducing the bug on my machine? That sounds dangerous.
sriramkalluri3
Great tool to triage the reported issues in bugs and fix them swiftly. This will definitely improves your productivity.
sriramkalluri3
Great tool to triage and fix the issues in bug. Improves your productivity massively.
majestic8
This looks very useful! What type of sandbox are you using? How does the mocking work?
rKulaSekhar
Love the focus on verification instead of just generating fixes.
vasmiReddy
Nice idea! The reproduce → verify loop is what makes this stand out.
ShaikMohammad
Very cool.Reproducing production bugs is usually the hardest part.
Bheemaneni
This seems especially used for teams handling production incidents.
Rishi1238
Interesting project. How does it handle services with multiple dependencies (queues, caches, third-party APIs)? Can it recreate enough of the production environment to reproduce intermittent bugs?
kumari_b
Interesting approach. The investigaion phase is usually the most time-consuming part of debugging. Curious how well this works on large, distributed systems.
shashi_ranjan
Nice work. The architecture looks well thought out, and it's refreshing to see engineering focused on reliability and developer experience rather than just adding AI buzzwords.
kirtivr
Thanks. As teams move faster with AI generated code, the focus on quality and reliability will have to increase as well.

And we will have to build better tools if we want to accelerate shipping velocity.

satyamtiwary
This is a really interesting direction. Bug fixing is always a painful part of software engineering. From reproducing issues, to identifying root causes, then generating fixes, and verifying them, it all adds to our project delivery timelines and this tool will definitely help in that aspect. Kudos to the development team for working on this product.
parspunisher
But how is this different from copilot?
kirtivr
A few different ways:

- Copilot may be better at implementing features. We're better at investigating bugs and fixing them.

- We handle huge context very easily. We specialize towards investigating large amounts of logs/metrics and traces.

- We do a lot of work to generate a non-trivial reproduction test case in a sandbox, which allows us to verify bug fixes. Ship confidently, not just based on the best available hypothesis.

- You can apply and remove code changes with the click of a button. We have an in-built VCS that allows you to add or remove sets of changes from a long coding session.

- Our pricing model is different. While with the standard Copilot developer plan you get $10 of AI usage (nothing if you're using Claude or GPT), we allow you unlimited triages on a fixed number of bugs. It's not about AI credits, it's about investigating and fixing complex bugs.

nxtcoder17
seems really interesting @kirtivr . Looking forward to it.

Though, i wonder if it could also be an integration to alerting platforms directly (like NewRelic, Datadog etc.), so that for on-call alerts, it could cover the foundation work, and have some hypotheses ready for the on-call engineer to directly jump into

kirtivr
This is on our roadmap!

At this time we are focussing on evaluation benchmarks like SWE-bench (verified). This is a simpler benchmark and does not really map well to investigating alerts that have a huge amount of context. But its a start.

I am wondering if we can improve upon foundation models with our reproduction <-> hypothesis loop approach.

Foundation models tend to be precision first, and context limited, so they can get sidetracked by various things.

This is an interesting problem to be working on right now!

omanhar
was there a technical constraint that you did not expect to have to solve or work around?