Did you know that Ellipsis can automatically write pull requests descriptions? The automated descriptions include context from your product roadmap and the team's recent work. As a developer pushes more commits, the summary will update, meaning that other engineers are always up-to-date on open pull requests.
Ellipsis (YC W24)
软件开发
New York,NY 2,724 位关注者
Automatically review code and fix bugs with AI
关于我们
Ellipsis will review your code (and do a good job!). Ellipsis helps engineers ship faster by providing automated code reviews and bug fixes. It's used by over 100 companies and installed in 19,000 codebases. Free 7 day trial available.
- 网站
-
https://www.ellipsis.dev/
Ellipsis (YC W24)的外部链接
- 所属行业
- 软件开发
- 规模
- 2-10 人
- 总部
- New York,NY
- 类型
- 私人持股
- 创立
- 2023
地点
-
主要
US,NY,New York,10010
Ellipsis (YC W24)员工
动态
-
“Ellipsis’s comments feel like they came from a tech lead, not a lintern" – by which he meant a linter turned up to 11.
We recently tested a handful of AI-driven PR review tools to see how they’d help us catch bugs, ensure code quality, and free up time to focus on functionality. Here’s what we learned from our experience in a Vercel Turborepo-based monorepo (TS packages, React apps, ShadCN, Tailwind, and a Python app): CodeRabbit Great for enforcing code standards, but not strong at catching implementation bugs. devlo Delivered some very insightful suggestions, but can get noisy with too many comments—some of which weren’t as helpful. Microsoft Copilot Provided fewer comments overall but nailed the summary. We couldn’t fully automate it for every PR (possibly our error). Ellipsis (YC W24) Our favorite! It filters out unhelpful or incorrect suggestions, so you only see high-quality comments. Plus, it incorporates our own feedback and guidelines seamlessly. ?? Our take: Yes! We have already fixed bugs manual review would have missed. (Always caused by Copilot of course - I promise the code we write manually is perfect ??) ? What AI-powered review or coding tools have you tried, and how did they compare? Let’s share insights!
-
-
I must say, its really nice to have tools like Ellipsis (YC W24). Just today i was about to submit a Pull Request into BAML's compiler to improve some of our errors for how we detect duplicate names in various scopes a user types in. Ellipsis was able to detect a really nuanced edge cases that cursor had auto completed wrong. Thanks Nick Bradford! Before -> After
-
-
Bugs like this are why your team needs an AI Code Review solution. Try it for free at www.ellipsis.dev
Ellipsis (YC W24) just caught the hidden gotcha of a lifetime. And saved me from taking down prod. Again. I intended to remove "[bot]" suffixes from a string, so I used the builtin rstrip() method. I had no idea that this removes any trailing combination of the characters passed as an argument, meaning if a GitHub username ends with "bot", "tob", "obo", "boot", etc., it would also be removed! See how "manwearingboot" becomes "manwearing"? That's because "boot" is made up of characters contained in the argument I passed, "[bot]". I've been working in Python for 15 years and I had no idea rstrip() behaves like this!! Thankfully, Ellipsis caught the bug and suggested the fix -> 1 click to resolve the problem.
-
-
Last week at the Y Combinator alumni retreat, I spoke to fellow AI founders on how we built Ellipsis (YC W24) to automate code review and bug fixes + how our dev workflow changed over the last year, including: ?? Composability is key: breaking hard problems into smaller LLM agents that can be independently benchmarked ???? Evals are all you need: we're investing deeply in annotating data and LLM-as-Judge ???? LLMs can help throughout the dev workflow: for example, on failed test cases, we use an LLM Auditor to auto-diagnose where in the agent's trajectory it went of the rails ?? Reducing false positives in code reviews: we've developed an extensive filtering pipeline to decrease noise and raise trust in the comments we leave, including new ways to leverage customer feedback ...and lots more! Link to full technical deep dive in comments ??
-
-
On February 18, join Tower Research Ventures in NYC for a Conference on Synthetic Software (CSS) 2025 — a private summit on the foundations and applications of generative code for the production of performant software. This is your chance to see demos and share ideas with the practitioners, researchers, and engineers who are reshaping the development landscape. In addition to Tower Research Ventures, speakers will include representatives from Ellipsis (YC W24), Codeflash, Princeton NLP, Daytona, and more. Reserve your spot today:?https://lu.ma/k2q27yi3 #GenerativeCode #AIInnovation
-
-
Not enough software engineers realize one of the most annoying/tedious parts of code review - checking for duplicated logic in your codebase - has been basically automated away using LLMs. -> Ellipsis (YC W24)
-
-
Automate the boring stuff with Reactive Workflows! Here are some examples: - "when the API is changed, create an issue to update the documentation" - "when a developer forgets to add docstrings, add them" - "when a bug report is opened, post in the #engineering slack channel" - "when a PR is opened without an associated issue, ask the author to add one" Generally available today. Try it out at www.ellipsis.dev
-
-
Introducing Reactive Workflows! ???? "Hey Ellipsis, when X happens, do Y" This is a powerful new feature for automating stuff in your GitHub repository. It's like Zapier for your codebase: - when a bug report is opened, post in the #bugreports Slack channel - when a code change modifies the Stripe integration, add me as a reviewer Learn more on Twitter: https://lnkd.in/eZ88hXKu
-
Big code means big risk for enterprises. LLM powered code reviews by Ellipsis mitigate that risk while allowing your team to move faster. Learn more: https://ellipsis.dev#demo
Why Ballooning Codebases Require Smarter Tools! As AI enhances our coding capabilities, the challenge of maintaining clean, secure, and scalable codebases grows. Hunter Brooks(Founder, Ellipsis (YC W24)) shares insights on using LLM-powered code reviews to tackle logical bugs and enhance software development workflows Full Episode: YouTube: https://lnkd.in/gC_YbxSS Spotify: https://lnkd.in/gAU3Ua5P Apple: https://lnkd.in/g8YZnKDE