“Engineers are becoming sorcerers” | The future of software development with OpenAI’s Sherwin Wu
Sherwin Wu leads engineering for OpenAI’s API platform, where roughly 95% of engineers use Codex, often working with fleets of 10 to 20 parallel AI agents.
We discuss:
1. What OpenAI did to cut code review times from 10-15 minutes to 2-3 minutes
2. How AI is changing the role of managers
3. Why the productivity gap between AI power users and everyone else is widening
4. Why “models will eat your scaffolding for breakfast”
5. Why the next 12 to 24 months are a rare window where engineers can leap ahead before the role fully transforms
—
Brought to you by:
DX—The developer intelligence platform designed by leading researchers
Sentry—Code breaks, fix it faster
Datadog—Now home to Eppo, the leading experimentation and feature flagging platform
—
Episode transcript: https://www.lennysnewsletter.com/p/engineers-are-becoming-sorcerers
—
Archive of all Lenny's Podcast transcripts: https://www.dropbox.com/scl/fo/yxi4s2w998p1gvtpu4193/AMdNPR8AOw0lMklwtnC0TrQ?rlkey=j06x0nipoti519e0xgm23zsn9&st=ahz0fj11&dl=0
—
Where to find Sherwin Wu:
• X: https://x.com/sherwinwu
• LinkedIn: https://www.linkedin.com/in/sherwinwu1
—
Where to find Lenny:
• Newsletter: https://www.lennysnewsletter.com
• X: https://twitter.com/lennysan
• LinkedIn: https://www.linkedin.com/in/lennyrachitsky/
—
In this episode, we cover:
(00:00) Introduction to Sherwin Wu
(03:10) AI’s role in coding at OpenAI
(06:53) The future of software engineering with AI
(12:26) The stress of managing agents
(15:07) Codex and code review automation
(19:29) The changing role of engineering managers
(24:14) The one-person billion-dollar startup
(31:40) Management lessons
(37:28) Challenges and best practices in AI deployment
(43:56) Hot takes on AI and customer feedback
(48:57) Building for future AI capabilities
(50:16) Where models are headed in the next 18 months
(53:35) Business process automation
(57:22) OpenAI’s ecosystem and platform strategy
(01:00:50) OpenAI’s mission and global impact
(01:05:21) Building on OpenAI’s API and tools
(01:08:16) Lightning round and final thoughts
—
Referenced:
• Codex: https://openai.com/codex
• OpenAI’s CPO on how AI changes must-have skills, moats, coding, startup playbooks, more | Kevin Weil (CPO at OpenAI, ex-Instagram, Twitter): https://www.lennysnewsletter.com/p/kevin-weil-open-ai
• OpenClaw: https://openclaw.ai
• The creator of Clawd: “I ship code I don’t read”: https://newsletter.pragmaticengineer.com/p/the-creator-of-clawd-i-ship-code
• The Sorcerer’s Apprentice: https://en.wikipedia.org/wiki/The_Sorcerer%27s_Apprentice_(Dukas)
• Quora: https://www.quora.com
• Marc Andreessen: The real AI boom hasn’t even started yet: https://www.lennysnewsletter.com/p/marc-andreessen-the-real-ai-boom
• Sarah Friar on LinkedIn: https://www.linkedin.com/in/sarah-friar
• Sam Altman on X: https://x.com/sama
• Nicolas Bustamante’s “LLMs Eat Scaffolding for Breakfast” post on X: https://x.com/nicbstme/status/2015795605524901957
• The Bitter Lesson: http://www.incompleteideas.net/IncIdeas/BitterLesson.html
• Overton window: https://en.wikipedia.org/wiki/Overton_window
• Developers can now submit apps to ChatGPT: https://openai.com/index/developers-can-now-submit-apps-to-chatgpt
• Responses: https://platform.openai.com/docs/api-reference/responses
• Agents SDK: https://platform.openai.com/docs/guides/agents-sdk
• AgentKit: https://openai.com/index/introducing-agentkit
• Ubiquiti: https://ui.com
• Jujutsu Kaisen on Crunchyroll: https://www.crunchyroll.com/series/GRDV0019R/jujutsu-kaisen?srsltid=AfmBOoqvfzKQ6SZOgzyJwNQ43eceaJTQA2nUxTQfjA1Ko4OxlpUoBNRB
• eero: https://eero.com
• Opendoor: https://www.opendoor.com
—
Recommended books:
• Structure and Interpretation of Computer Programs: https://www.amazon.com/Structure-Interpretation-Computer-Programs-Engineering/dp/0262510871
• The Mythical Man-Month: Essays on Software Engineering: https://www.amazon.com/Mythical-Man-Month-Software-Engineering-Anniversary/dp/0201835959
• There Is No Antimemetics Division: A Novel: https://www.amazon.com/There-No-Antimemetics-Division-Novel/dp/0593983750
• Breakneck: China’s Quest to Engineer the Future: https://www.amazon.com/Breakneck-Chinas-Quest-Engineer-Future/dp/1324106034
• Apple in China: The Capture of the World’s Greatest Company: https://www.amazon.com/Apple-China-Capture-Greatest-Company/dp/1668053373
—
Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email podcast@lennyrachitsky.com.
—
Lenny may be an investor in the companies discussed.
To hear more, visit www.lennysnewsletter.com
How OpenAI Builds for 800 Million Weekly Users: Model Specialization and Fine-Tuning
In this episode, a16z GP Martin Casado sits down with Sherwin Wu, Head of Engineering for the OpenAI Platform, to break down how OpenAI organizes its platform across models, pricing, and infrastructure, and how it is shifting from a single general-purpose model to a portfolio of specialized systems, custom fine-tuning options, and node-based agent workflows.
They get into why developers tend to stick with a trusted model family, what builds that trust, and why the industry moved past the idea of one model that can do everything. Sherwin also explains the evolution from prompt engineering to context design and how companies use OpenAI’s fine-tuning and RFT APIs to shape model behavior with their own data.
Highlights from the conversation include:
• How OpenAI balances a horizontal API platform with vertical products like ChatGPT
• The evolution from Codex to the Composer model
• Why usage-based pricing works and where outcome-based pricing breaks
• What the Harmonic Labs and Rockset acquisitions added to OpenAI’s agent work
• Why the new agent builder is deterministic, node based, and not free roaming
Resources:
Follow Sherwin on X: https://x.com/sherwinwu
Follow Martin on X: https://x.com/martin_casado
Stay Updated:
If you enjoyed this episode, be sure to like, subscribe, and share with your friends!
Find a16z on X: https://x.com/a16z
Find a16z on LinkedIn: https://www.linkedin.com/company/a16z
Listen to the a16z Podcast on Spotify: https://open.spotify.com/show/5bC65RDvs3oxnLyqqvkUYX
Listen to the a16z Podcast on Apple Podcasts: https://podcasts.apple.com/us/podcast/a16z-podcast/id842818711
Follow our host: https://x.com/eriktorenberg
Please note that the content here is for informational purposes only; should NOT be taken as legal, business, tax, or investment advice or be used to evaluate any investment or security; and is not directed at any investors or potential investors in any a16z fund. a16z and its affiliates may maintain investments in the companies discussed. For more details please see http://a16z.com/disclosures
Stay Updated:
Find a16z on YouTube: YouTube
Find a16z on X
Find a16z on LinkedIn
Listen to the a16z Show on Spotify
Listen to the a16z Show on Apple Podcasts
Follow our host: https://twitter.com/eriktorenberg
Please note that the content here is for informational purposes only; should NOT be taken as legal, business, tax, or investment advice or be used to evaluate any investment or security; and is not directed at any investors or potential investors in any a16z fund. a16z and its affiliates may maintain investments in the companies discussed. For more details please see a16z.com/disclosures.
Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.
DevDay 2025: Apps SDK, Agent Kit, MCP, Codex and why Prompting is More Important than Ever
At OpenAI DevDay, we sit down with Sherwin Wu and Christina Huang from the OpenAI Platform Team to discuss the launch of AgentKit - a comprehensive suite of tools for building, deploying, and optimizing AI agents. Christina walks us through the live demo she performed on stage, building a customer support agent in just 8 minutes using the visual Agent Builder, while Sherwin shares insights on how OpenAI is inverting the traditional website-chatbot paradigm by embedding apps directly within ChatGPT through the new Apps SDK.
The conversation explores how OpenAI is tackling the challenges developers face when taking agents to production - from writing and optimizing prompts to building evaluation pipelines. They discuss the decision to adopt Anthropic’s MCP protocol for tool connectivity, the importance of visual workflows for complex agent systems, and how features like human-in-the-loop approvals and automated prompt optimization are making agent development more accessible to a broader range of developers.
Sherwin and Christina also reveal how OpenAI is dogfooding these tools internally, with their own customer support at openai.com already powered by AgentKit, and share candid insights about the evolution from plugins to GPTs to this new agent platform. They discuss the surprising persistence of prompting as a critical skill (contrary to predictions from two years ago), the challenges of serving custom fine-tuned models at scale, and why they believe visual agent builders are essential as workflows grow to span dozens of nodes.
Guests:
* Sherwin Wu: Head of Engineering, OpenAI Platform https://www.linkedin.com/in/sherwinwu1/ https://x.com/sherwinwu?lang=en
* Christina Huang: Platform Experience, OpenAI https://x.com/christinaahuang https://www.linkedin.com/in/christinaahuang/
Thanks very much to Lindsay and Shaokyi for helping us set up this great deepdive into the new DevDay launches!
Key Topics:• AgentKit launch: Agent SDK, Builder, Evals, and deployment tools• Apps SDK and the inversion of the app-chatbot paradigm• Adopting MCP protocol for universal tool connectivity• Visual agent building vs code-first approaches• Human-in-the-loop workflows and approval systems• Automated prompt optimization and “zero-gradient fine-tuning”• Service Health Dashboard and achieving five nines reliability• ChatKit as an embeddable, evergreen chat interface• The evolution from plugins to GPTs to agent platforms• Internal dogfooding with Codex and agent-powered support
Full Video Episode
Timestamps
00:00 Welcome to the OpenAI Dev Day Studio
01:11 Dev Day Evolution and Community Growth
03:08 Apps SDK and ChatGPT Distribution Strategy
05:27 MCP Protocol Integration Decision
09:26 Agent Kit Launch and Platform Vision
11:33 Agent Builder Canvas and Visual Workflows
17:22 Evaluations and Agent Testing Evolution
19:20 Automated Prompt Optimization and Research
26:35 Connector Registry and MCP Servers
34:10 Chat Kit as Consumer-Grade Infrastructure
39:13 Codex Power User Tips and AI-Native Development
42:27 Service Health Dashboard and Reliability Journey
This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.latent.space/subscribe
Inside OpenAI Enterprise: Forward Deployed Engineering, GPT-5, and More | BG2 Guest Interview
Open Source bi-weekly convo w/ Bill Gurley and Brad Gerstner on all things tech, markets, investing & capitalism. This week, guest host Altimeter’s Apoorv Agrawal explores how OpenAI is reshaping enterprise with Sherwin Wu, Head of Engineering OpenAI Platform, and Olivier Godement, Head of Product OpenAI Platform. From T-Mobile’s AI voice support to Amgen’s drug breakthroughs to Los Alamos’ air-gapped supercomputer—this episode dives into the real world of AI at scale. Enjoy another episode of BG2!
Timestamps:
(00:00) Intro
(01:50) OpenAI’s Enterprise Mission: Beyond ChatGPT
(06:00) Case Study: T-Mobile <> Voice & Support
(11:30) Case Study: Amgen <> Accelerating Drug Development
(13:45) Case Study: Los Alamos National Lab
(17:00) Why 95% of AI Deployments Fail?
(20:30) Physical vs Digital Autonomy: Scaffolding & Infrastructure
(26:00) GPT-5: Release, Benchmarks vs Behavior
(30:00) GPT-5 Feedback: Instruction Following, Hallucinations, Code Quality
(33:00) Multimodality: Text, Voice, and Video
(35:30) Audio: Realtime API vs Stitched Audio
(38:00) Model Customization & Reinforcement Fine-Tuning (RFT)
(43:00) Rapid Fire: Long/Short Picks
(1:03:00) Highlights and Lowlights @ OpenAI
Show Notes:
T-Mobile Partnership: https://www.t-mobile.com/news/business/t-mobile-launches-intentcx-with-openai
Amgen Partnership: https://openai.com/index/gpt-5-amgen/
Los Alamos Partnership: https://www.lanl.gov/media/news/0130-open-ai
MIT AI Report: https://mlq.ai/media/quarterly_decks/v0.1_State_of_AI_in_Business_2025_Report.pdf
Produced by Dan Shevchuk
Music by Yung Spielberg
Available on Apple, Spotify, www.bg2pod.com
Follow:
Brad Gerstner @altcap https://x.com/altcap
Bill Gurley @bgurley https://x.com/bgurley
BG2 Pod @bg2pod https://x.com/BG2Pod
Apoorv Agrawal @apoorv03 https://x.com/apoorv03
Sherwin Wu @sherwinwu https://x.com/sherwinwu
Olivier Godement @oliviergodement https://x.com/oliviergodement