Lenny's Podcast: Product | Career | Growth
Lenny's Podcast: Product | Career | Growth

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

September 8, 2025

AI Summary

5 min read

Cognition CEO Scott Wu describes Devin as an autonomous AI software engineer that integrates into tools like Slack, Linear, and GitHub to handle end-to-end tasks, from planning to pull requests. Launched in March 2024 after starting as a November 2023 hackathon project, Devin has evolved through eight pivots within coding agents, improving from high-school CS level to junior engineer capabilities, though with "jagged intelligence"—stronger than humans in some areas, weaker in others.

Internal Operations with Devin
Cognition's 15-engineer team runs up to five Devins per engineer asynchronously, with Devin currently authoring about 25% of pull requests and merging several hundred monthly into production codebases. By year-end, they expect over 50% Devin-authored PRs. Engineers hand off well-defined tasks (e.g., bug fixes, features), review plans or code, and intervene on complex parts, enabling parallel work while focusing on architecture over implementation.

Continue reading the full summary in the app — free to try.

Read Full Summary →

Free • No credit card required

Listen to Audio Summary Open in App

What you'll learn

  • 1 (00:00) **🎙️ Introduction: Scott Wu**
  • 2 (06:00) **What is Devin?**
  • 3 (06:51) **Devin's Seniority Evolution**
  • 4 (09:15) **Devin's Scale and Usage**
  • 5 (10:23) **Origin Story of Cognition**
  • 6 (14:08) **Pivots and Timeline**
  • 7 (17:25) **Devin's Personality and Workflow**

+ Full timestamped outline available in the app

Show Notes

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

Vanta—Automate compliance. Simplify security.

—

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 DeepWik

Lenny's Podcast: Product | Career | Growth

More from this podcast

Lenny's Podcast: Product | Career | Growth →