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. In this conversation, Scott demonstrates how his team uses their own product to accelerate development workflows, reduce engineering toil, and handle routine tasks asynchronously. Scott walks us through real examples of how Devin integrates into Cognition’s daily operations—from researching and implementing new features to responding to crashes and handling frontend fixes. He explains how Devin differs from traditional AI coding assistants by functioning more like a team member than a tool, allowing engineers to delegate well-scoped tasks while focusing on higher-level problems. *What you’ll learn:* 1. How to use DeepWiki to research your codebase and generate better prompts for AI engineering tasks 2. A workflow for treating AI agents as asynchronous junior engineers who can handle multiple tasks while you attend meetings 3. Why public channels create better learning environments for both humans and AI when implementing engineering solutions 4. The top five engineering tasks AI excels at: frontend fixes, version upgrades, documentation, incident response, and testing 5. How to implement a “first line of defense” system where AI agents analyze crashes before humans need to intervene 6. A technique for bringing voice AI into meetings as an additional participant to answer questions without disrupting flow *Brought to you by:* Google Gemini—Your everyday AI assistant: https://ai.dev/ Vanta—Automate compliance. Simplify security: https://www.vanta.com/howiai *Where to find Scott Wu:* X: https://x.com/ScottWu46 LinkedIn: https://www.linkedin.com/in/scott-wu-8b94ab96/ *Where to find Claire Vo:* ChatPRD: https://www.chatprd.ai/ Website: https://clairevo.com/ LinkedIn: https://www.linkedin.com/in/clairevo/ X: https://x.com/clairevo *In this episode, we cover:* (00:00) Introduction to Scott Wu and Devin (03:53) Where Devin excels (06:08) Using DeepWiki to research codebases and create better prompts (10:27) Prompting tips (11:24) The asynchronous nature of working with Devin (13:38) Multithreading tasks (14:43) Using Devin to implement an MCP server integration (18:38) Setting up workflows in Slack for first-line responses (23:22) Encouraging AI adoption in public Slack channels (25:50) Top five engineering tasks for Devin (32:17) Using ChatGPT voice as a meeting participant (35:57) Lightning round *Tools referenced:* • Devin: https://devin.ai/ • DeepWiki: https://deepwiki.org/ • ChatGPT: https://chat.openai.com/ • Windsurf: https://windsurf.ai/ • Slack: https://slack.com/ • Linear: https://linear.app/ • GitHub: https://github.com/ *Other references:* • MCP (model context protocol): https://www.anthropic.com/news/model-context-protocol • TanStack Router: https://tanstack.com/router/ _Production and marketing by https://penname.co/._ _For inquiries about sponsoring the podcast, email jordan@penname.co._

Scott WuguestClaire Vohost

Sep 7, 202541mWatch on 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

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.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.