By playing, you agree to uListen's Terms and Privacy Policy and YouTube's Terms of Service.

How Devin replaces your junior engineers with infinite AI interns that never sleep | Scott Wu (CEO)

Scott Wu is the co-founder and CEO of Cognition Labs, the creators of Devin, an AI agent designed to function as a junior engineer on software development teams.

Scott WuguestClaire Vohost

Sep 7, 202541mWatch on YouTube ↗

Summaries, chapters, transcripts, and FAQs on this page are made by uListen, not YouTube.

WHAT IT’S REALLY ABOUT

Devin as async AI intern: tasks, workflows, and adoption tips

Scott Wu (Cognition Labs CEO) explains Devin as an asynchronous “junior engineer” optimized for well-scoped tasks rather than open-ended architectural problems.
They demo a workflow using DeepWiki to understand a repo, generate a high-context prompt, and launch a Devin session that researches an external MCP server (ChatPRD) and produces a GitHub pull request.
The conversation highlights how Slack/Linear-based, public-by-default “multiplayer” collaboration helps teams both teach the agent and upskill humans through shared prompting patterns.
They close with tactical “top tasks” Devin excels at (frontend fixes, upgrades, docs, incident response, tests) and an additional tip: using ChatGPT voice as an audible meeting participant to reduce friction for quick fact-finding.

IDEAS WORTH REMEMBERING

5 ideas

Devin performs best on clearly scoped tasks, not vague “problems.”

Wu frames Devin as a junior engineer: strong at executing defined work (e.g., add an MCP integration, fix a UI behavior) but not the primary driver for big architectural strategy.

Use a sync step (Wiki/Search) to set up the async step (agent execution).

DeepWiki helps you rapidly map the codebase and relevant files; that context is then transformed into a stronger prompt before you “hand off” to Devin asynchronously.

Prompt refinement is a leverage point—turn the 5-word ask into a spec-like prompt.

Instead of “add X,” the workflow generates a detailed prompt referencing patterns, types, files, and checks—reducing retries and making the async run more reliable.

Asynchronous agents unlock “multithreading” across many workstreams.

Because you don’t babysit execution, you can kick off 2–10 tasks in parallel, then periodically review progress, diffs, screenshots, and PRs when convenient.

Institutionalize Devin as first-line response in Slack for reactive engineering.

Cognition tags Devin on issues, crashes, and small requests so it can triage, propose fixes, and open PRs—humans then do targeted review and final polish.

WORDS WORTH SAVING

5 quotes

Devin is async. Once you kick off a Devin session, Devin's gonna start working... but you're not expected to be there with it.

— Scott Wu

Devin's my favorite intern on my team, and I have infinite of them.

— Claire Vo

Tasks, not problems.

— Scott Wu

If you had an intern... would you just send them a five-word Slack message?

— Scott Wu

I almost think of ChatGPT voice as, like, a better Google.

— Scott Wu

Read the available transcript

Async agent vs synchronous toolsTasks-not-problems framingDeepWiki repo understanding and prompt constructionPR-oriented execution loop and verification (diffs, screenshots)Slack/Linear workflows and public channels for adoptionMultiplayer collaboration and knowledge accumulationVoice mode in meetings as “better Google”

High quality AI-generated summary created from speaker-labeled transcript.

Get more out of YouTube videos.

Read along on your phone, search it beside the video, or ask your favorite AI app what was said.