Our eng team put Devin on the on-call rotation. It investigates alerts, finds the root cause, and opens a tested PR for review.
Excited for our friends at @cognition to be officially launching this one!
Introducing Devin Oncall: Devin automatically investigates alerts and bugs, helping your team diagnose and resolve production incidents.
Devin Oncall already handles thousands of alerts every day for some of the world’s largest companies. Let it become your SRE today.
Introducing American Forge: a six-month residency for exceptional engineers ready to take on the toughest problems in American government.
Run by National Design Studio in partnership with @cognitionforge.ndstudio.gov/?s=x
Huge congrats to @cognition for taking the #1 spot on #SREGym! 🎉
It’s been incredible to have a front-row seat to the progress in AI SRE. Shoutout to @anhangz, @yunpark93, and @jake_rachleff for an amazing release pushing the frontier of autonomous incident response.
One step closer to a world where humans don't have to be on call. 🚀
SREGym 1.1 is out now, with 2.0 on the way to push the frontier even further.
📊 Follow the progress: sregym.com
📝 More on Devin Oncall: devin.ai/blog/introduci…
Introducing Devin Oncall: Devin automatically investigates alerts and bugs, helping your team diagnose and resolve production incidents.
Devin Oncall already handles thousands of alerts every day for some of the world’s largest companies. Let it become your SRE today.
Devin can now build and test iPhone Duo apps in macOS cloud VMs
Unfold the phone, fold it, close it, check every screen, and get video verification of everything. Here are some examples:
1. Devin takes someone's portrait while they watch themselves on the outside screen, it
Introducing American Forge: a six-month residency for exceptional engineers ready to take on the toughest problems in American government.
Run by National Design Studio in partnership with @cognitionforge.ndstudio.gov/?s=x
Nobody at Rox writes evals anymore.
Devin now QAs our agent every week, on real traffic.
It reads real conversations with our agent, rebuilds each failure in a full copy of Rox, and turns it into an eval. We just review the PR.
The eval suite already covers 72% of real usage
Engineers are realizing they don’t need to lose as much sleep while on call anymore.
Correspondingly, usage even while in private beta has been explosive
Introducing Devin Oncall: Devin automatically investigates alerts and bugs, helping your team diagnose and resolve production incidents.
Devin Oncall already handles thousands of alerts every day for some of the world’s largest companies. Let it become your SRE today.
Devin Oncall is finally here! We took all of our learnings over the last two years around making agents good at resolving production issues, and taught Devin to do it all.
Self-driving software is here.
Introducing Devin Oncall: Devin automatically investigates alerts and bugs, helping your team diagnose and resolve production incidents.
Devin Oncall already handles thousands of alerts every day for some of the world’s largest companies. Let it become your SRE today.
Devin Oncall detects emerging problems before customers notice them, allowing teams to act early and contain incidents before they escalate.
Engineers can focus on building the future, not maintaining the past.
Introducing Devin Oncall: Devin automatically investigates alerts and bugs, helping your team diagnose and resolve production incidents.
Devin Oncall already handles thousands of alerts every day for some of the world’s largest companies. Let it become your SRE today.
Most LLMs need to load an essay of text just to conclude “yes” or “no.”
If a step only needs to route a ticket, tag an intent, or flag a policy violation, sending it through a large generative LLM to produce JSON is overhead.
That’s why the new decision models are worth a look.
@typesafeai Jev (hosted) and
Kev by @jaredpalmer@cognition
(open weights, Apache 2.0) don’t generate text at all.
devkick, @dabit3@cognition, and @UofT Machine Intelligence Student Team (UTMIST) are putting on an event this Saturday, capped at 60 where each attendee will get $200 Devin credits to build Decision use cases.
Join us on Saturday, it will fill up fast: Luma link in comments.
.@strellic and I did a full 1:1 file-by-file port of Minecraft from Java to Rust
both the server and client are ported -- there are some perf bugs but it does appear to work!
Gemini 4 Argon is now available in Devin Desktop and CLI.
On FrontierCode 1.1, Gemini 4 Argon scores 60.5%, making it the highest performing Gemini model on the leaderboard.
Through October 27th it is available at 75% off for Devin users.
Dynamic workflows let Devin split a big job into pieces, hand each one to its own Devin, and bring the results back together.
The plan for a Dynamic Workflow lives in code instead of an agent’s head, so you always know which Devins will run, in what order, and what each one is told.
203 Followers 4K FollowingGraphic designer, web developer, gardener, and wildlife rehabber from Kentucky.
Staunchly anti-Trump, pro-democracy, and radically progressive.
191K Followers 8 FollowingMakers of Devin, the first AI software engineer. We are an applied AI lab building end-to-end software agents. Join us: https://t.co/4Ss9hvpjRG