Recent posts
プロアクティブな自動化がセットアップされたときのプログラミングがどれほど違うか、人々は気づいてないと思う。 Cognition 内のすべての重要な Slack チャネルで、Devin のオートメーションがすべての投稿を監視してる。トリアージ、解決、ルーティング、レビュー。Devin はコードベースのどの部分を誰が担当してるかを知ってて、フィードバック/承認のために誰をループに入れるべきか、いつ意見を言うべきか黙ってるべきかをわかってる。 エンジニアリングの進捗の基盤となるハムは今ほぼ完全に自動化された。エンジニアは将来のプロダクト方向性の大きな賭けをナビゲートする一方、Devin は現状を保守・ポーランドしてる。
原文を表示 (en)
I don't think people realize how different programming feels when proactive automations are set up. On every important Slack channel inside Cognition, we have a Devin automation monitoring all posts - triaging, solving, routing, reviewing. Devin knows who works on which parts of the codebase, who to loop in for feedback / approval, and when to chime in vs. stay silent. The baseline hum of engineering progress is almost entirely autonomous now. Engineers steer the big bets for future product directions while Devins maintain and polish the status quo.
I'm genuinely mind blown by how good @DevinAI automations are it's the first product to nail the UX and execution of this kind of thing for me (having tried claude/codex equivalents)
Cognition 前 / Devin 後
原文を表示 (en)
Before Cognition / After Devin
コーディングエージェントに手動でプロンプトを入力して仕事させるのは、間もなく UX のバグのように感じられるようになるでしょう。 未来はオートメーションを設定して、ログインする頃にはエージェントが既に仕事を完了しているという状態です。過去数ヶ月間、この機能をたくさん実装してきました。本日、Auto-Triage を公開できて興奮しています！
原文を表示 (en)
Having to manually prompt your coding agent to do work will soon feel like a UX bug. The future is setting up automations so that your agent already does the work by the time you log on. We've shipped a ton of functionality around this over the past few months. Excited to release Auto-Triage publicly today!
Introducing Devin Auto-Triage: Your AI first-responder with long-term memory. Devin can monitor incoming bugs, alerts, and incidents, investigate them, and come back with context, next steps, or a PR.
Really enjoyed this conversation with @JTLonsdale on what’s happening in agentic software engineering and what it means for the rest of the world.
EPISODE 147: The New Era of Software Abundance @JTLonsdale visits @ScottWu46 & @russelljkaplan at @cognition HQ 00:00 Episode intro 01:35 Why technical talent & execution matters in AI 06:10 Do young people have an edge in the AI era? 08:26 Cognition's rapid growth 11:55 The new era of software abundance 14:30 Cognition engineers don't type code anymore 19:20 "Never sleep while Devin is idling" 21:25 The case for AI disinflation 23:50 How Devin generates 12X productivity gains 28:25 Cognition for government / taking on complex, broken systems 36:40 The AI race / competition with Anthropic 39:00 Forward deployed engineers? 43:40 How fast are LLMs improving? 47:10 The AI-led small business explosion
My brain dump of predictions about the future, the impact of software agents on government, what AI companies can learn from the self-driving race, whether the SaaSpocalypse is real, and the history of punch cards, with @jordanschneider.
new show with @cognition's @russelljkaplan on what software abundance could mean for state capacity. https://t.co/4r9Jhw6Jo6 we get into: Why government software is so broken — Despite spending over $100B annually on IT, critical systems at agencies like the Social Security Administration and U.S. Department of the Treasury still run on decades-old code that few engineers know how to modify. How two-year software projects become three-week ones — why AI agents are particularly good at the painful migration and modernization work engineers tend to avoid. What “software abundance” actually means — AI agents can handle the tedious work of switching systems 24/7, collapsing the switching costs, and forcing software vendors to compete on value rather than locking customers into outdated systems. AI for cybersecurity — From triaging massive vulnerability backlogs to automatically fixing CVEs, AI will be essential for defending critical infrastructure as attackers gain the same tools. The coming “post-coding” world — As models converge in capability, the key bottleneck shifts from writing code to understanding problems, reviewing systems, and deciding what should be built in the first place.
Aston Martin 🤝 Cognition Grateful that Aston Martin has chosen Cognition as its AI software engineering partner. Time to build.
Welcome to the team, @cognition. The dedicated AI coding agent company joins us as a Global Partner. Find out more: https://www.astonmartinf1.com/en-GB/news/announcement/aston-martin-aramco-signs-cognition
Most AI code review tools are bots that comment on your PRs. The results sometimes feel like “fighting slop with slop”. We’re trying a different approach with Devin Review: 100% human-in-the-loop, with lots of AI leverage. The goal is true understanding, not vibe merging. The interface at https://t.co/rGJCPzF3t7 feels a bit like context engineering for humans. Glad to see the positive feedback so far!
wow, have been using @cognition's new PR review tool. think whatever you want of devin. but this is incredible. also makes it *really* obvious how vulnerable GitHub is.
Cognition's in-house model, SWE 1.5, is now the best free coding model in the world
Introducing Wave 13: Shipmas Edition 🎅 - SWE-1.5 Free: The full intelligence of SWE-1.5 at standard throughput, for free for the next 3 months - True parallel agents with Git Worktrees + multi-pane and multi-tab Cascade - Dedicated terminal for more reliable command execution And many other other new features, bug fixes, and performance improvements. Happy holidays and merry shipping from the Cognition team!
High state capacity in software engineering matters! This is great to see - kudos @skupor and team. Consider applying. For those who join and later look to move to the private sector, @cognition will have an accelerated interview track specifically for Tech Force alumni.
Join an elite group of technologists to transform the federal government through modern software development. Go to http://TechForce.gov to apply today
We gave Devin a 2025 performance review. Quite a few examples and metrics in here from our thousands of customers of where these agents succeed and struggle. Should be interesting to anyone thinking about how to deploy coding agents in the real world.
Devin, the AI software engineer, just got its 2025 performance review! Over the past eighteen months, thousands of companies have hired Devin, including Goldman Sachs, Citi, Santander, and Nubank. Using real-world examples and metrics from customers, we looked at where Devin shines and where it struggles. You might find this interesting if you’re thinking about deploying coding agents in the real world. Read the full review here: https://t.co/AWDkbJVgzz Major takeaways: 🧵
