Autonomous Engineering Pipelines are incredibly powerful, but how do you actually build one? The hard parts aren't the agent, they're the plumbing: - Orchestrating triggers across Slack, GitHub, Linear, DataDog, Sentry, and other services. - Duplicate detection - Long-term memory - Noise filtering: deciding which messages actually need investigation - Conditional filtering - Routing tables - Tagging the right code owner - Linking new alerts to existing threads instead of spawning redundant sessions Devin has all of this built in. This walkthrough teaches how to set your own pipeline up in < 10 minutes:

Last chance to fill out the annual AI Engineering Survey this weekend and win great Vercel Notion AIE tix! link below we had @devinai analyze registered attendee list and output a live chart of the people coming to the conference. it ended up being the single best data driven storytelling i've ever seen on what kind of community we are gathering in two weeks. survey link here! ntn.so/ai-survey no lurking, fill it out pls

devin has been nice. i only talk to a single agent (on ultra), which handles all my agents for me. it's great to not think about agent sequencing anymore. or merge conflicts! i also tell my agent manager stuff like "i'll be gone" or "i'm tired", and it reallocates accordingly.

If you're a researcher looking to: → conduct rigorous studies on how multiple models can outperform the frontier → leverage data from the largest LLM marketplace (150 trillion tokens processed per month) ... DM me with your work! We have an exciting role coming in the future, but might fill it opportunistically.

been using devin this month thanks to @buildfutureto for pro plan. its built really well. This is the first cloud agent that feels good for real coding. I am ripping through PRs. there is no branch picker, which surprisingly is nice & devin review w/ auto fixes is a beast. might have to get a pro plan for devin after this trial.

how to solve all your problems using claude code, fable, and @cognition devin: 1. use fable cc workflows to plan work and create linear issues 2. point a devin ultra agent at linear, and tell it to implement everything by spinning up separate gpt 5.5/fable sessions 3. profit

Come join us!

lines of code as a metric is officially dead

After spending the week in Europe with some of our largest banking customers, one thing is clear: the market is moving beyond AI adoption and into value realization. Last year, the question was “How do we deploy AI?” Today, it’s “What outcomes are we getting?” @ryanbai1412’s latest post outlines how we think about measuring and delivering results with @DevinAI at @cognition.

introducing: the singularity ft. @DevinAI

/handoff is one of the most powerful features of Devin CLI: close your laptop, your agents keep working from the cloud. Now, we've open sourced it.

We've open sourced my favorite Devin feature: /handoff Hand off jobs to cloud Devins from your local machine Install it as a plugin in Claude Code or Codex or any other coding agent Close your laptop without pausing your agents 😉

@DevinAI does a lot of things right but one of the things it does best is knowing its own capabilities and configurations. Changing something is as simple as asking, no searching in settings, no ui work, just ask to make an automation or delete an automation and it just works

Hey Vancouver! On July 4th @cognition is hosting: Agents Of Chaos luma.com/vmerbbas A hackathon where the gloves come off. Two tracks to choose from: - Be an agent of change - Be an agent of chaos $3000.00 im Devin credits to win Use Devin agent to build or destroy

Devin is now the best data analyst in the world angellist.com/blog/everyone-…

i deeply apologize for making fun of devin by @cognition six months ago i was not aware of your game devin is really really really useful and good

$100k in prizes for the Inference-Time Compute Hackathon happening June 19-20 in SF. 24 hour hackathon with three tracks: - ​Agents - ​Real-Time Interactive - ​Talent Marketplace Applied AI Hosted by @cognition, @mercor_ai, @Etched, and @AnthropicAI

Lots of people asked how I used Fable to edit its own launch video so I made a video about that! TLDR it wrote a lot of code & tool calls to use transcription services, ffmpeg, do colorgrading, use the figma mcp, make remotion UI and render it. I didn't touch a video editor.