@imjaredz: Since I joined @cognition I've been obsessed with learning how our eng team uses Devin themselves If we are building th…
Summary
An engineer at Cognition shares internal tips for using Devin, including the 'Agent Fan Out' technique where a master agent spins up parallel child agents to solve tasks independently.
View Cached Full Text
Cached at: 06/20/26, 08:23 PM
Since I joined @cognition I’ve been obsessed with learning how our eng team uses Devin themselves
If we are building the best coding agent + we have the most cracked engineers + we’ve been fully AI-pilled from day one… it stands to reason that there is a lot to learn by just watching our technical staff work
And yes there are a lot of tips & tricks. I recorded a video talking about my favorite…
Agent Fan Out - asking your agent to break down the problem, spin up 10 more agents in parallel, and combine their results
This is something I’ve seen everyone do
- from our model research team spinning up 100 Devins to examine eval logs
- or our product team using 5 child Devins to try out 5 different alternative implementations of the same thing
If engineering is cheap and easy, why not build the product 10 times and choose the best one?
Think of it in a master/slave context: Master Devin -> 10 Slave Devins -> Master Devin pulls their results
There are two reasons this is useful
- Agents are smartest when their context is small and their task is small & precise. Context windows are finite and too much becomes distracting
- Agents are good at helping you break a large problem into independent & parallelizable chunks of work
Every Devin is its own VM/computer so this also is just a great way to move faster. I’ve done a migration from React Native to Swift by having Devin break it up into 6 pieces then spin up new Devins to work in parallel
In the video I build a greenfield project and try my best to show off this agent fan out concept.
I also threw in a few other tricks that I’ve seen my coworkers do:
- Let Devin write its own prompts (especially for creating child Devins). It’s way better than us humans
- Do tons of things at once. You should be absolutely frying your attention span. Your job should just be babysitting 38 different Devins
- Don’t be a blocker. Before letting the agent work I make sure to tell it to ask me any questions that would fill in ambiguities. Give your agent all the information it needs (and then some more) so that it can just cook without stopping to ask you questions every few minutes
- Let Devin test itself. Integration sanity tests are pretty much solved
Hope this is useful!!
And please ignore the lights… I left “party mode” on by accident in our basement speakeasy
Inspired by
this is a really long post @imjaredz …
proof my attention span is still healthy and functioning
now you get it!!
mogging is a state of mind
thanks man!
Similar Articles
@imjaredz: We've open sourced my favorite Devin feature: /handoff Hand off jobs to cloud Devins from your local machine Install it…
Devin's /handoff feature has been open-sourced, allowing users to hand off jobs to cloud Devins from their local machine and install it as a plugin in coding agents like Claude Code or Codex.
@Chris_Wozniczek: Not sure if anyone of you checked out @DevinAI from @cognition but here I found a quick guide on some of the features. …
A quick guide highlights features of Devin AI, an autonomous AI software engineer from Cognition, including integrations with Slack, terminal, and project management tools.
@walden_yan: If you're building your own cloud agent like Devin or Ramp Inspect, there's lots of great details here on setting up VM…
A deep dive into building cloud agents with Walden Yan (Cognition) and Cole Murray (OpenInspect), covering VM setup, computer use, memory, and the rise of async agents in the AI engineering landscape.
@russelljkaplan: I don't think people realize how different programming feels when proactive automations are set up. On every important …
A Cognition employee describes how Devin automations monitor Slack channels, triaging and solving issues autonomously, making engineering progress almost entirely autonomous while engineers focus on big bets.
@cognition: Introducing Devin Auto-Triage: Your AI first-responder with long-term memory. Devin can monitor incoming bugs, alerts, …
Cognition introduces Devin Auto-Triage, a new feature for Devin that adds long-term memory and autonomous monitoring of bugs, alerts, and incidents, with the ability to investigate and propose fixes or pull requests.