Hunter Brooks

Ellipsis (YC W24) - AI code reviews & bug fixes

AI Code Reviews that automatically catch logical bugs, anti-patterns, documentation drift, and can even enforce your team style guide. Simply open a PR to get a code review. Then, if any bugs are found, squash them with 1-click Bug Fixes. Free trial available.

Add a comment

Replies

Best
Hunter Brooks
Hi ProductHunt, Hunter and Nick here! Allow me to introduce Ellipsis, a GitHub bot that automatically performs deep, LLM-powered code reviews, fills in PR descriptions, and can even write working, tested code to fix bugs. Simply open a pull request to get an AI Code Review and summary. As you keep pushing code, Ellipsis will update the summary and review the new changes. If a bug pops up, you can squash it with 1-click fixes. ๐Ÿš€ Here's an example from jxnl/instructor (10K stars) ๐Ÿš€ ๐Ÿ‘จโ€๐Ÿ’ป What does it catch? Ellipsis will catch logical errors, anti-patterns, security issues, spelling & grammar mistakes, documentation drift, and more. Reviews take less than 3 minutes. You can even have Ellipsis enforce your team style guide rules, like this project. For example, you might add a rule like "Make sure new code has corresponding unit tests." Ellipsis will subsequently leave reminders on any pull requests that try to submit untested code. ๐Ÿ› How does it fix bugs? When Ellipsis finds a problem, it'll leave a comment on the offending line, just like a human would. Then, you can tag Ellipsis to have it implement the fix. This allows you to write working, tested code right from the GitHub UI! Internally, Ellipsis actually tests the code it writes by building your project, running the unit tests, linter, etc. ๐Ÿ†’ ๐Ÿš€ Why did we build this? We built Ellipsis because we are TIRED of the status quo code review process: create a PR, ask for review, move on to new task, receive feedback, reacquaint with old code, fix bug, go back to new task... there's too much context switching. With Ellipsis, the reviews are nearly instant and addressing feedback doesn't require checking out an old branch. โ“ Does it work? Yes. State-of-the-art LLM's aren't good enough (yet) to implement entire features, but they are good enough to catch and fix small mistakes in code. Our data shows that teams that use Ellipsis merge pull requests 13% faster than those that don't. Typically, a developer will get a "Looks good to me!" from Ellipsis before asking for a peer review, resulting in a higher quality discussions with fewer [nit] comments. Start a free trial to get 7 days of AI Code Reviews at ellipsis.dev ๐Ÿค–
Emma Lawler
Awesome stat that teams are merging 13% faster - curious if this is across all types of features or if you've noticed a particular pattern of where it works best? One of the most expensive delays I notice on our engineering team is time spent waiting for someone to review. They have to finish up whatever deep work they're doing to quickly get up to speed on a new problem and make sure nothing will break. Excited to try it out and see how it helps us ship features faster and more incrementally.
Hunter Brooks
@emmalawler24 great question! Ellipsis can actually test the code it writes, so it's very powerful when used by teams with good test coverage, this tends to be teams adding features (or fixing bugs) on the backend
ulearnr
@hunter_brooks Currently Ellipsis is using which ai models?
Hunter Brooks
@ulearnr all of them ๐Ÿ˜Ž seriously, we use a variety of agents on the backend which call a variety of models
Javid Jamae
Several of my teams have been using Ellipsis for 4-5 months now and the code reviews and ticket summaries are on point. It constantly catches things that human reviewers would have missed. Itโ€™s been a great tool!
Hunter Brooks
@javid_jamae Thanks! What do you think of the automatic PR summaries?
Javid Jamae
@hunter_brooks ah yes, thatโ€™s what I meant by ticket summaries. The PR summaries have been really useful!
Hunter Brooks
@javid_jamae great to hear, thanks!
Gado
Nice job! @hunter_brooks Congrats on the launch ๐Ÿš€
Gabriel R
Very cool application, and super excited for documentation drift!
Arindam Majumder
This is really interesting, It will really Open Source maintainers like me. Great work Team Ellipsis.๐Ÿ‘๐Ÿผ All the best for the launch ๐Ÿ”ฅ
Hunter Brooks
@arindam_1729 Thanks - we love sponsoring open source, so don't hesitate to reach out
Geoffrey Gu
Congrats on the launch! Developer workflows will definitely be improved!
Angela Ni
Congrats on the launch @hunter_brooks! How does it ensure the generated code snippets are optimized for performance and best practices?
Hunter Brooks
@angela_ni2 ellipsis reviews its own code ๐Ÿ˜Ž
Tony Han
Ha LGTM-as-a-service! Love the little humor there. This honestly is a great addition especially if the team is stretched super thin and tech leads don't have time to do good code reviews. I've seen junior engineers suffer because tech leads don't give good reviews and they leave as a result. I assume the AI can leverage style guide you created so it will stay consistent and personalize the reviews? Congrats on the launch @hunter_brooks and team!
Hunter Brooks
@tonyhanded Exactly - we automatically infer your style guide AND allow you to "hardcode" it into a YAML file
Olivia Jane Mitchell
This is an impressive tool, Hunter! The ability to catch logical bugs and enforce style guide rules with minimal hassle will definitely streamline our code review process. It's great to see LLMs being used effectively in this wayโ€”speeding up PRs by 13% is a significant improvement. I canโ€™t wait to give the free trial a go and see how it enhances our workflow. Thanks for sharing this with the community! ๐Ÿš€
Patricia Harris
Ellipsis sounds like a game-changer for code reviews, Hunter! The ability to catch logical errors and enforce style guide rules automatically is exactly what teams need to reduce context switching and improve productivity. I love the 1-click bug fix feature - it's so efficient! Plus, merging PRs 13% faster is impressive; this could really enhance the build process for many devs. Can't wait to see how it progresses! Definitely upvoting this!
Hunter Brooks
Thanks, @patriciaharris! Ask a developer you know to try it out - we offer a free 7 day trial
Konrad S.
Looks very promising! Really useful application of AI.
Hunter Brooks
@konrad_sx Thanks! We think AI isn't yet good enough for large scale code generation, but is perfectly suited for code review and bug fixes. Our documentation has more info on this: https://docs.ellipsis.dev
Mr. ร…nand
Congrats on the launch!๐ŸŽ‰ Ellipsis features shown in demo looks impressive.
Hunter Brooks
@astrodevil Thanks! It's not just a demo, 100+ companies pay for Ellipsis today. $20/month/developer for PR Summaries, a 2nd pair of eyes on pull requests, and easy bug fixes is an easy win for everyone
William Jin
Congrats on launching Ellipsis! How does the AI adapt to different coding styles?
Hunter Brooks
@william_jin Very well - that's the power of using a LLM.
Kyrylo Silin
Hey Hunter, How does Ellipsis handle more complex logic bugs that might not be as straightforward to catch? Is there any mechanism for users to help train it on specific types of errors they encounter often? Congrats on the launch!
Hunter Brooks
@kyrylosilin Yes! If you express a rule, Ellipsis will check for it in every review. Examples: - โ€œMake sure the docstrings are always accurate when a function is updatedโ€ - Always user ID in log statements, never user name/address/phone number/etc - All new code in src/ needs unit tests, except for the frontend code in src/frontend/
SEN
๐Ÿ™Œ Love the idea of squashing bugs with just one clickโ€”let's be honest, who doesnโ€™t want to skip the back-and-forth hassle of traditional reviews? With the power of LLMs, it seems you're on the cutting edge of making developersโ€™ lives easier. I'm curious how it handles edge casesโ€”any plans for extending its capabilities besides catching those anti-patterns? Also, will there be a way to customize the review process even further based on team requirements? Looking forward to seeing how it evolves! ๐Ÿš€ #PHCommunity #Makers
Hunter Brooks
@big_tree Teams can customize the things that Ellipsis reviews for using rules: https://docs.ellipsis.dev/featur...
Elke
This is a game changer, Hunter! The deep LLM-powered reviews sound incredibly efficientโ€”no more endless context switching. I love how Ellipsis not only catches those pesky bugs but also helps enforce team style guidelines. Itโ€™s like having an extra teammate thatโ€™s always on top of things. ๐Ÿš€ The fact that teams merge PRs 13% faster is a compelling metric! This could really improve our workflow. Iโ€™m definitely going to give the free trial a shot. Canโ€™t wait to see how it enhances our coding process!
William Jin
Makes finding and resolving code issues seamless! Handled diverse tech already, here?
Hunter Brooks
@william_jin We support many languages/frameworks, which do you use?
Ben Gale
This looks great! Is there certain languages or frameworks it works better with, or not at all?
Hunter Brooks
@bengale great question! We see best results with Python, Ruby, JavaScript/TypeScript, Java, C++. Basically, if ChatGPT is helpful to you, Ellipsis will be
Star Boat
Congratulations on launching Ellipsis, Hunter! ๐Ÿš€ This sounds like a game changer for the code review process. The ability to automatically catch logical bugs and enforce team style guides will definitely save developers so much time and effort. Love the idea of squashing bugs with just 1-click fixes; thatโ€™s going to make the workflow so much smoother. The integration with GitHub and the real-time updates on PR descriptions is a feature that will surely enhance collaboration within teams. Itโ€™s impressive to see how Ellipsis can help reduce context switching and boost productivity by 13%. This is exactly the innovation us Makers need in our dev toolkits! Canโ€™t wait to try out the free trial and see how it improves our code quality. Wishing you all the success with this launch! Keep up the great work!
Chris Dossman
Excellent product Hunter. We have been using it for months and can't go back, the whole engineering team loves it.
Nick Bradford
@cdossman awesome!! definitely let us know of any feedback or feature requests ๐Ÿ™