The Pragmatic Engineer

chevron_right

Building Windsurf with Varun Mohan

whatshot 676 snips

May 7, 2025

Guest

Varun Mohan

Varun Mohan, the CEO and Co-Founder of Windsurf, shares his insights on creating an AI-native IDE after a background in autonomous vehicles. He discusses the unique challenges of coding with LLMs, including their lack of certain capabilities. Varun emphasizes how Windsurf improves developer productivity and fosters a culture of learning from failure. He also highlights innovative techniques for reducing latency in cloud performance and enabling non-developers to build custom SaaS applications, reshaping the future of software engineering.

01:27:54

forum

Ask episode

web_stories

AI Snips

view_agenda

Chapters

menu_book

Books

auto_awesome

Transcript

info_circle

Episode notes

insights

INSIGHT

AI Boosts Developer Productivity Ceiling

AI increases the productivity ceiling for software development, enabling developers to build more.
This higher ROI empowers companies to create better products faster.

insights

INSIGHT

AI Empowers Developer Confidence

Windsurf lets engineers fearlessly explore and change unfamiliar code areas.
Developers increasingly turn to AI first for ideas before coding changes.

insights

INSIGHT

AI Reduces Developer Fatigue

Software engineering has unique mental fatigue due to iterative problem-solving and incomplete code.
AI tools reduce activation energy, easing developer cognitive load and burnout.

Get the Snipd Podcast app to discover more snips from this episode

Evaluating AI Models in Windsurf

01:39 • 5min

chevron_right

Enhancing Software Development through AI and Code Review

06:23 • 2min

chevron_right

Navigating the Windsurf Revolution

08:30 • 23min

chevron_right

The Crucial Role of Latency in Cloud Performance

31:38 • 2min

chevron_right

Innovative Code Indexing Techniques

33:40 • 8min

chevron_right

Balancing Innovation and User Needs

41:57 • 21min

chevron_right

Engineering Windsurf: Choices and Challenges

01:03:01 • 21min

chevron_right

Navigating AI, Endurance Sports, and Innovation

01:24:00 • 4min

chevron_right

#32884

• Mentioned in 2 episodes

Showstopper

Anya Wallach

Lisa Fiedler

Showstopper, by Charles Petzold, provides an in-depth account of the development of Windows NT. It details the technical challenges, managerial decisions, and the sheer scale of the project. The book offers insights into the complexities of operating system design and the human element involved in such a massive undertaking. Petzold masterfully weaves together technical explanations with compelling narratives of the individuals who shaped Windows NT. The book serves as a valuable resource for software engineers and anyone interested in the history of computing.

#3113

• Mentioned in 15 episodes

The Idea Factory

Bell Labs and the Great Age of American Innovation

Jon Gertner

The Idea Factory traces the origins of some of the twentieth century's most important inventions, such as the transistor, laser, digital communications, and cellular telephony. The book focuses on the lives and work of brilliant and eccentric scientists like Mervin Kelly, Bill Shockley, Claude Shannon, John Pierce, and Bill Baker, who spent their careers at Bell Labs. It delves into the organizational structure and strategies that enabled Bell Labs to sustain a golden age of innovation, including the physical layout designed for serendipitous interactions and the creation of courses to diffuse knowledge. The book also distinguishes between 'invention' and 'innovation,' highlighting Bell Labs' involvement in the full vertical stack from theory to marketable products.

Supported by Our Partners

•⁠ Modal⁠ — The cloud platform for building AI applications

•⁠ CodeRabbit⁠⁠ — Cut code review time and bugs in half. Use the code PRAGMATIC to get one month free.

—

What happens when LLMs meet real-world codebases? In this episode of The Pragmatic Engineer, I am joined by Varun Mohan, CEO and Co-Founder of Windsurf. Varun talks me through the technical challenges of building an AI-native IDE (Windsurf) —and how these tools are changing the way software gets built.

We discuss:

• What building self-driving cars taught the Windsurf team about evaluating LLMs

• How LLMs for text are missing capabilities for coding like “fill in the middle”

• How Windsurf optimizes for latency

• Windsurf’s culture of taking bets and learning from failure

• Breakthroughs that led to Cascade (agentic capabilities)

• Why the Windsurf teams build their LLMs

• How non-dev employees at Windsurf build custom SaaS apps – with Windsurf!

• How Windsurf empowers engineers to focus on more interesting problems

• The skills that will remain valuable as AI takes over more of the codebase

• And much more!

—

Timestamps

(00:00) Intro

(01:37) How Windsurf tests new models

(08:25) Windsurf’s origin story

(13:03) The current size and scope of Windsurf

(16:04) The missing capabilities Windsurf uncovered in LLMs when used for coding

(20:40) Windsurf’s work with fine-tuning inside companies

(24:00) Challenges developers face with Windsurf and similar tools as codebases scale

(27:06) Windsurf’s stack and an explanation of FedRAMP compliance

(29:22) How Windsurf protects latency and the problems with local data that remain unsolved

(33:40) Windsurf’s processes for indexing code

(37:50) How Windsurf manages data

(40:00) The pros and cons of embedding databases

(42:15) “The split brain situation”—how Windsurf balances present and long-term

(44:10) Why Windsurf embraces failure and the learnings that come from it

(46:30) Breakthroughs that fueled Cascade

(48:43) The insider’s developer mode that allows Windsurf to dogfood easily

(50:00) Windsurf’s non-developer power user who routinely builds apps in Windsurf

(52:40) Which SaaS products won’t likely be replaced

(56:20) How engineering processes have changed at Windsurf

(1:00:01) The fatigue that goes along with being a software engineer, and how AI tools can help

(1:02:58) Why Windsurf chose to fork VS Code and built a plugin for JetBrains

(1:07:15) Windsurf’s language server

(1:08:30) The current use of MCP and its shortcomings

(1:12:50) How coding used to work in C#, and how MCP may evolve

(1:14:05) Varun’s thoughts on vibe coding and the problems non-developers encounter

(1:19:10) The types of engineers who will remain in demand

(1:21:10) How AI will impact the future of software development jobs and the software industry

(1:24:52) Rapid fire round

—

The Pragmatic Engineer deepdives relevant for this episode:

• IDEs with GenAI features that Software Engineers love

• AI tooling for Software Engineers in 2024: reality check

• How AI-assisted coding will change software engineering: hard truths

• AI tools for software engineers, but without the hype

—

See the transcript and other references from the episode at ⁠⁠https://newsletter.pragmaticengineer.com/podcast⁠⁠

—

Production and marketing by ⁠⁠⁠⁠⁠⁠⁠⁠https://penname.co/⁠⁠⁠⁠⁠⁠⁠⁠. For inquiries about sponsoring the podcast, email podcast@pragmaticengineer.com.

Get full access to The Pragmatic Engineer at newsletter.pragmaticengineer.com/subscribe

Home Top podcasts Popular guests Top books