cofounder @ellipsis_dev (YC W24), a Managed Agent Platform for Developers. You choose the model, harness, prompts, and tools. We'll handle the infrastructure.
New York, NY
Joined June 2020
- Tweets1.1K
- Following3.6K
- Followers1.5K
- Likes3.8K
FYI: The CEO of @coderabbitai is sharing takes like this. If you are a Code Rabbit customer, here is how you can migrate off and own your own code review agent:
1) Install @ellipsis_dev
2) Add a `code_review.yaml` to Github
3) Get code reviews
What we are seeing at @coderabbitai and elsewhere on this parabolic trajectory is that even larger seed rounds ($8M+) are no longer enough to build a software business. Software factories need quality tokens and large-scale compute to run CI, sandboxes, and other infrastructure to ship software at scale. At this point, smaller startups exist only to funnel ideas to larger startups with more tokens.
If you want to build agents without vendor lock in, check out @ellipsis_dev.
You choose the model, harness, tools. Ellipsis handles the VMs, permissions, logs, budgets.
Building your own version is as simple as adding a code_review.yaml file
See: ellipsis.dev/docs/code-revie…
I’ll be demo’ing @blinkdotreview, code review that runs in the agent loop after every file edit.
hosting the first ever jev by @typesafeai demo night in new york next week
space is limited. looking for all types of demos.
register: luma.com/xogxfokf
want to demo: docs.google.com/forms/d/e/1F…
game changer
Introducing blink.review, blazing fast code review for your coding agent.
It runs automatically every time the agent makes a file change. Check it out: blink.review
@CompleteSkeptic I've built a CLI for codebase search using Jev, can I get off the waitlist to test?
Search works by walking the git node tree, directory by directory. Next step, using an ensemble of walkers to create a posterior distribution
github.com/ellipsis-dev/blin…
Looking through the @ellipsis_dev database today and saw one of the first 100 github accounts ever created: @door_holder
Most importantly, code generation is a domain where validating the LLMs output (lint, compile, test) is cheap
AI coding agents offer the best glimpse into what the future of agents will look like in many other fields of knowledge work.
AI coding has accelerated faster than any other AI space because the builders of AI understand their own workflows deeply, and they’re incentivized to improve it for their own productivity.
It’s also a great petri dish because the ecosystem will adopt new tools (and dump old ones) faster than other space, which gives you better signal faster to what paradigms work and which don’t. The darwinian forces are very strong here.
While there are plenty of things that don’t translate from coding to other areas of knowledge work, in agents it’s clear that we’re starting to see the formulation of the core primitives for agents in knowledge work.
These foundations include: background agents that you kick off in a simple GUI or via another logical trigger, the ability to track their progress, add in relevant context, ability to pull in additional signal and tools, ways of reviewing the work and output at the end of the workflow, creating custom agents on the fly when workflows are repeated, and so on.
We’re in the earliest phases of what this will look like across software, but the fuzziness that we had a year ago is starting to get a bit more clear by the day. Incredible times ahead.
Hunter Brooks 😎 retweeted
The deadline to apply for the YC Fall 2025 batch is this Monday, August 4th.
All you need is an idea: ycombinator.com/apply
Today's reason why AI Code Review by @ellipsis_dev is important to your business:
businessinsider.com/anthropi…
Interesting observation: today's AI Agents will call you out if you have a bug in your tool implementation code
This didn't used to be the case in 2023.
SOTA models in 2025 are smart enough (or confident enough?) to detect bugs in your logic, which is a black box to the agent
Hunter Brooks 😎 retweeted
man, @ellipsis_dev is so underrated. of the code review AIs we use on GitHub, Ellipsis is consistently the best one, every single time
Hunter Brooks 😎 retweeted
Out enjoying a Saturday with my partner meanwhile @cognition_labs Devin and @ellipsis_dev are cranking out PR’s.
We’re about to start deploying daily with no human interaction. Ellipsis approval on a PR is going to trigger auto merge and deploy.
Replit and others in the code gen space are growing like crazy, but (very important!!) if you're writing code with AI, you should also be reviewing code with AI!
AI Code Reviews & Bug Fixes from @ellipsis_dev install into your repository in 2 clicks
