Abstract
Details coming soon.
Register
$2,955, Conference (3 days). Current pricing ends October 13th. All pass options.
76%
senior dev or higher
1:11
speaker ratio
60+
practitioners
QCon San Francisco 2026 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.
Part of the track
Architecting for Agents: Beneath the Loop Hosted by Julie Amundson Senior AI Infrastructure Consultant, ex-Googler, ex-NetflixerFrom the same track
Wednesday 18 November
10:35 Ballroom BC Session AI Platform Engineering for Agents Mark Khuzam Senior Software Engineer @Netflix, Previously Led the Consumer Web Platform Team @OpenTable Agentic tools amplify what’s already in the codebase. The agent works through your code, your architecture decisions, and the documentation around them. It follows what it can read and guesses at the rest. 11:45 Ballroom BC Session AI/ML Avoiding Prompt Debt: Building Resiliant AI Apps that Grow With the Ecosystem Drew Breunig CEO & Cofounder CMPND, Editor of O'Reilly's "Context Management Handbook", Writer on AI & Data at dbreunig.com, Previously Data Science & Product Lead PlaceIQ Details coming soon. 13:35 Ballroom BC Session AI/ML Infrastructure for Agents Details coming soon. 14:45 Ballroom BC Session Dreams on Paper: How Agents Learn from Experience Brian Douglas Co-Founder & CEO @Paper Compute Co., Previously Founded Open Sauced and Led Developer Advocacy @GitHub Agents produce high-fidelity traces of everything they do. But traces alone don't produce memory. This talk introduces three primitives for turning session history into something actionable: 15:55 Ballroom BC Session Making Production Legible to Agents: Lessons From Building an Observability MCP Liz Fong-Jones Technical Fellow @honeycomb.io, Developer Advocate, Labor and Ethics Organizer, and Site Reliability Engineer (SRE), Over Two Decades of Experience An agent that can query production telemetry can test its own hypotheses against reality, rather than hallucinate fictions. Observability tooling allows our agents to close the loop and benefit from production wisdom.