Speaker
Abstract
Claude Code is the first developer tool built specifically to maximize AI development velocity. People routinely try to dissect it looking for its secret sauce or advanced architecture, but the key parts of the implementation are just some async generators and nicely typed interfaces composed with basic orchestration patterns. The real technical innovation wasn't building sophisticated systems—it was deliberately choosing simple solutions that maximize development velocity. In this talk, we'll explore the architectural decisions that prioritize speed over complexity, and how this velocity-first approach naturally leads to process-product convergence where internal workflows evolve into user-facing capabilities.
Main Takeaways:
- Simple by Design: Why deliberately simple patterns in high level languages that support async generators and typed interfaces outperform complex AI systems when speed is the primary competitive advantage
- Process-Product Convergence: How rapid iteration cycles blur the lines between development workflows and product features, with concrete examples from Claude Code's evolution
- Engineering for Speed: Technical patterns for rapid release, update, and feedback gathering that enable acceleration at scale
Interview
The majority time in my day is spent working on Claude Code:
- Low-level implementation details like Claude’s shell and its integration with native tooling
- Build and release process
- Installer and auto-updater
AI agents are reshaping the landscape of software development practices faster than we can settle on shared best practices. As an engineering community, we will have to work together to figure out how to get the most from these incredible tools. So much of what makes Claude Code great is grounded in feedback from our users.
Software engineer, AI engineer, Product Manager, Technical Program Manager, Designer
Topics
QCon San Francisco 2025 is a three day conference for senior software engineers, architects and team leads. An international program committee of working engineers selects every session. Patterns and practices, not products and pitches.
From the same track
Tuesday 18 November
10:35 Ballroom BC Session AI Agents Engineering at AI Speed: Lessons from the First Agentically Accelerated Software Project Adam Wolff Engineer and Individual Contributor to Claude Code @Anthropic, Previously @Robinhood, @Facebook Claude Code is the first developer tool built specifically to maximize AI development velocity. 11:45 Ballroom BC Session Engineering AI for Creativity and Curiosity on Mobile Bhavuk Jain Tech Lead @Google This talk shares practical lessons from building production-grade AI for creativity and curiosity on mobile devices. 13:35 Ballroom BC Session AI/ML Improving Meta Generative Ad Text using Reinforcement Learning Alex Nikulkov Research Scientist (RL lead for Monetization GenAI) @Meta Reinforcement Learning with Performance Feedback (RLPF) unlocks a new way of turning generic GenAI models into customized models fine-tuned for specific tasks. This approach is especially powerful when combined with in-house data and performance metrics. 14:45 Seacliff ABC Session AI Agents From Content to Agents: Scaling LLM Post-Training Through Real-World Applications and Simulation Faye Zhang, Andi Partovi This talk presents a comprehensive journey through modern AI post-training techniques, from Pinterest's production-scale content discovery systems to enterprise agent training through Veris AI’s simulation. 15:55 Ballroom BC Session Dynamic Moments: Weaving LLMs into Deep Personalization at DoorDash Sudeep Das, Pradeep Muthukrishnan In this talk, we’ll walk through how DoorDash is redefining personalization by tightly integrating cutting-edge large language models (LLMs) with deep learning architectures such as Two-Tower Embeddings (TTE) and Multi-Task Multi-Label (MTML) models. 17:05 Ballroom BC Session AI/ML Automating the Web With MCP: Infra That Doesn’t Break Paul Klein Founder @Browserbase, previously Director of Self-Service & Engineering Manager @Mux, Co-Founder & CTO @Stream Club, Technical Lead @Twilio Inc. AI agents are only as strong as the infrastructure beneath them. In this talk, we’ll walk through the architecture behind Browserbase’s model context protocol (MCP), built to support stateful browser automation at scale.