Engineering Production Systems for an Agentic Era: QCon San Francisco 2026

QCon San Francisco 2026 will bring together practitioners from Airbnb, OpenAI, Netflix, Honeycomb, and other engineering organizations to share how they build, operate, and evolve production systems as AI agents take on a larger role, according to the conference announcement. The event runs November 16–20 at the Hyatt Regency San Francisco, with the conference on November 16–18 and training on November 19–20. Early-bird conference tickets are available for $2,955 through October 13.

Weiping Peng, Distinguished Engineer at Airbnb, will present "How Airbnb Guardrailed Its AI Customer Support Agent," covering safeguards behind an agent that serves millions of customers, maintains context across conversations, and can initiate account actions. The talk will discuss a layered approach including input sanitization, classifiers, shadow testing, false-positive management, and rapid-response mitigations.

Brian Yang, Member of Technical Staff at OpenAI, will present "Lessons from Building a $100M Product in Six Weeks at OpenAI," sharing the operating model used to build OpenAI Ads with coding agents and scale it to more than $100 million in annual recurring revenue in under six weeks. The session covers feedback loops, verification, token economics, and decisions that remained under human ownership.

Netflix engineers Joseph Lynch and Ayushi Singh will present "Orderly Keys, Wild Values: Adaptive Compression for Distributed Key-Value Storage," examining compression across billions of daily requests and petabytes of key-value data, including trade-offs among storage footprint, cache behavior, network I/O, p99 latency, dictionary versioning, compatibility, and rollout safety.

Honeycomb Technical Fellow Liz Fong-Jones will present "Making Production Legible to Agents: Lessons From Building an Observability MCP," sharing lessons from an MCP server used by more than 40% of Honeycomb's weekly active users to run production queries through agents. The session covers token economy, tool descriptions, schemas, evaluations, output formats, and defects found in real-world use.

Khawaja Shams, QCon San Francisco 2026 Program Committee member and co-founder and CEO of Momento, said Vidhya Arvind, Track Host and Tech Lead and a Founding Architect for the Data Abstraction Platform at Netflix, put together a program covering latency, consistency, failure handling, observability, capacity, and operational trade-offs at scale.

The InfoQ Certified Architect Program combines the three conference days with a peer cohort and a half-day workshop on November 19 led by Luca Mezzalira. Participants earn the ICSAET certification. Optional hands-on training on November 19–20 covers choosing an SDK for AI agents, AI-native development with harness engineering, Claude Code and Codex, measuring developer productivity, incident response and learning, and AI-assisted coding workflows.