Cognition announced Devin Bots on X on November 17. You give a Bot a goal; it breaks the work down, starts a Devin session for each piece, and runs them in parallel, each on its own cloud machine, through coding, testing and review until the PR is ready to merge, surfacing only the decisions that need you. Bots can run on schedules and triggers, such as watching Slack for customer issues or checking CI every night. Cognition says beta testers merge 4.5x more PRs per message on average.
Key Takeaways
- ✓How it works: give a Devin Bot a goal and it breaks the work down and runs several Devin sessions in parallel, each on its own cloud machine, following each one until the PR is ready to merge
- ✓Communication: talk to Bots over Slack, group chats, text or phone calls; deploy approvals, missing keys and trade-off decisions land in a single "Needs you" list
- ✓Always on: Bots can set schedules and triggers, such as watching Slack for customer issues, checking CI nightly or monitoring Linear for blockers; Bots also hand work to each other, for example a QA Bot passing a bug to a Developer Bot
- ✓Numbers: Cognition says beta testers merge 4.5x more PRs per message on average and that some engineers went from 50 PRs a week to nearly 2,000; these are Cognition's own figures
- ✓Templates: the site offers Software Factory, Android Engineer, Chief of Staff, Latency Optimizer, Product Engineer and QA Engineer templates; separate pricing has not been published

Key Decision Metrics at a Glance
Turn your technical choice into a development budget
Compare 40 dev plans & simulate token costs vs $20/mo subscriptions
Project Links & Resources
Direct AccessIn-Depth Technical Analysis
Background
Most coding agents today work one session at a time: a developer files a request, waits for the result, then files the next one. As tasks pile up, the human becomes the dispatcher, splitting work, tracking progress and chasing merges. Devin Bots, which Cognition launched on November 17, hand that coordination layer to AI as well: one persistent Bot leads a team of Devins.
How it works
You give a Devin Bot a goal and it splits the work into sub-tasks, starting a Devin session for each. Every session runs on its own cloud machine and goes through planning, coding, automated testing and Devin Review until the PR is ready to merge. Bots can set schedules and triggers, such as watching Slack for customer issues, verifying CI health every night or monitoring Linear for blockers. Bots also work together: a QA Bot finds a bug and hands it to a Developer Bot to fix, while a PM Bot posts progress in Slack. Decisions that need a human, such as approving a production deploy, adding an API key or choosing whether to keep an old endpoint, are collected in one place.
Numbers that matter
Cognition has not published standard benchmark results, only beta data: testers merge 4.5x more PRs per message on average, and some engineers went from 50 PRs a week to nearly 2,000. These are Cognition's own figures and have not been independently verified.
What it means for developers
You can start at devin.ai/bots, with ready-made templates including Software Factory, Android Engineer, Chief of Staff, QA Engineer, Product Engineer and Latency Optimizer. You can direct Bots over Slack, text, phone calls or group chats. Enterprise features include SSO, SCIM, audit logs, zero data retention with model providers and a separate VM for every session. Pricing for Bots has not been published separately, so start with a narrow job such as automated bug fixing or PR QA before handing over larger goals.
Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.