Introducing Fusion in Devin CLI
The most efficient frontier harness for Fable & Astra; 39% cheaper across coding benchmarks.
Pick your favorite model for planning and a cost-effective model for execution.
GPT-6 Astra is coming to Devin.
We're giving away 50 free Devin Max Plans ($10,000 in value) for anyone wanting to try it!
Reply below with what you you're building (or want to build). I'll notify winners in 24 hours. ⚡
GPT-6 Astra is coming to Devin.
On FrontierCode 1.1, Astra performs within 0.4 points of Fable 5 at a 64% lower cost. It also sets a new SOTA on our internal testing benchmark, generating more comprehensive tests, clearer reports, and better video evidence.
In a world where teams are burning through token budgets without clear ROI, we've developed scalable ways to measure the value of agents' work. And now we're offering customers up to $10M in guaranteed output with Devin.
Today we're excited to launch Devin Desktop.
It's compatible with Codex, Claude Agent, OpenCode, and any other ACP-compatible agent.
With this launch, the @DevinAI platform covers all major surface areas - Cloud, CLI, Desktop, Automations, Testing, and Review - the platform tackles the full SDLC.
We're proud to support great models and great agents wherever they come from, because the best work happens when you're free to pick the right tool for the job.
Excited to keep building here. ⚡️
We've seen lots of enthusiasm for Devin's end-to-end testing capabilities in its virtual machine.
In this post, @ido_pesok shares the technical details behind how we implement testing for verification at scale.
By end of year I think 95%+ agent sessions will come from automations and events. We already see this happening @cognition where more than 50% of Devin customer sessions are triggered by non-humans.
Learning how to build these types of systems will be a valuable skill.
In this video I walk through how to get started with event-driven agentic systems with Devin, starting with transforming Slack into an agent-native control plane.
You can extend this to GitHub events, schedules, and arbitrary webhooks while maintaining traceability, auditability, and session attribution with @devinai.
Big thing just happened
For the first time, more Devins are being triggered by agents than by humans. events, schedules, other Devins
Our vision from day one is that Devin will be a teammate, not just something in your toolbox
Devin should work while you take a walk & while you sleep. it should be the first responder to Datadog errors and user feedback.
it should be proactive, not reactive
Devin Auto-Triage gets smarter with every incident.
Devin can remember prior investigations, deduplicate related reports, link threads and tickets, map team ownership areas, and keep track of recurring issues.
Beau Rothrock had been at @AngelList for two months when he walked into a Redshift-to-Snowflake migration in deep trouble, already two months behind schedule.
He had a 5-week window to migrate all 14,000 dashboards and reports AngelList runs on.
He could've asked for three more engineers and four more months. Instead, he turned to Devin.
The answer to out of control token spend is cloud agents
when you give someone arbitrary *local* token spend you don't really know what they're doing or how they're using it
but with cloud agents like @devinai all usage is traceable therefore you have visibility into everything including token waste
this also encourages developers to be more thoughtful about their prompting and usage
Learn Devin in 5 minutes
Cloud agent. Terminal agent. Linear assignee. Slack teammate. On schedule. Devin is everywhere your engineering team already lives.
00:00 - Introduction
00:19 - Sending sessions to @SlackHQ
00:24 - Creating your first session
00:51 - Devin Review
01:20 - Computer Use testing
01:46 - Desktop and IDE in Devin
02:33 - Scheduled Devins
03:01 - Devin for Terminal
03:40 - Terminal to cloud handoff
04:09 - DeepWiki
04:21 - Assigning Devins from @linear
If you got this far, I'm giving away $1,000 in Devin credits, $200 to 5 people for a free month of Devin Max.
Comment what you'd like to build and retweet this post to be eligible to win!
Starting to test out Devin for Terminal, and comparing to Codex. Using Devin's model to start, SWE-1.6 Fast.
And holy moly, is it fast.
Just day one though, so nothing to report back yet w/respect to code quality, but the speed is definitely impressive.
Intelligence at 1000 tokens per second, right in your terminal.
Now available with SWE-1.6 Fast, powered by @cerebras.
We're giving the first 100 people who respond a free month of Max to try it out.
Devin Review caught the axios supply chain attack for multiple Cognition customers before the attack was publicly known.
These attacks will be 10x more frequent in the age of AI; it is critical that repo maintainers start using AI for defense as well.
(showing one example below where Devin Review caught the attack within an hour of its release - text minorly edited for anonymization)