Keynote
When Software Becomes a User: Identity and Authorization for Agents in Production
CTO @1Password, Founded and Scaled AWS Data Protection, Previously @Rubrik and @Google
QCon AI New York 2026 / sessions
The talks confirmed so far
QCon AI New York 2026 is two days of senior engineers and architects walking through the agent runtimes, context pipelines, eval loops and security controls they run in production, and what they would do differently.
The full schedule is published closer to the event. Until then, every talk appears on this page as the program committee confirms it.
December 15–16, 2026
The Westin Jersey City Newport
20 of 30+ talks confirmed
Past attendees included senior engineers from
Program
Talks and keynotes
Session
A Software Factory Build Report: What Worked, What Broke, What I'd Do Again
Java Champion and Head of Developer Relations @Tessl, Focused on Developer Tooling, Application Security, and AI-Native, Spec-Driven Software Development
Session
After It Works: Trusting and Teaching Alchemy, DoorDash's AI Moderation Platform
Software Engineer @DoorDash, 10+ Years in Software Engineering
Session
Session
Agents That Improve Over Time: Lessons from Shipping an Optimizer
Principal Research Software Engineer @Microsoft Research, Core Contributor to AutoGen, Author of "Multi-Agent Systems with AutoGen" Book, Previously @Cloudera, @IBMResearch
Session
Be Your Toughest Customer: Shipping Collaborative Agents Twice, to Our Own Org and to Lawyers
Software Engineer @Harvey
Session
Benchmarking Voice Agents in the Wild: Mapping the Capability Gap Between Text and Voice
Research Engineer @Sierra, Previously Research Engineer at ASAPP and Conducted NLP Research at Cornell
Session
Bring the Power of On-Device AI to Life with Google AI Edge and Gemma
Senior Staff Software Engineer @Google AI Edge, 20 Years of Experience in Google's Core Engineering & Research Groups
Session
Building in the AI-First World: Scale Brilliance, Not Bottlenecks
Lead of DORA and Product Manager @Google Cloud
Session
Building On-Device Health Models with Small, Medium, and Massive Datasets
Director of Women’s Health @Google, Previously Founded the Women's Health Science Team @Oura
Session
Session
From Intent to Enforcement: Open-Source Evaluation and Governance for AI AgentsPresentation
Principal PM Manager @Microsoft, Co-Founded Error Analysis, Fairlearn, and Responsible AI Toolbox
Session
High-Signal AI Code Review That Adapts to Your Codebase at Scale
Principal Staff Engineer @LinkedIn, Caltech CS PhD With Over 20-Year Extensive Software Development Experience
Session
Session
Make Each Token Count: Compression, Caching, and Retrieval for Production LLM Context
CEO and Co-Founder @Headroom Labs, IEEE Senior Member, and BCS Fellow, Previously @Netflix
Session
One Infrastructure, Every Model: How Netflix Scales ML & GenAI
Staff Software Engineer @Netflix
Session
Reflections on the 2x initiative at Honeycomb
Technical Fellow @honeycomb.io, Developer Advocate, Labor and Ethics Organizer, and Site Reliability Engineer (SRE), Over Two Decades of Experience
Session
Supercomputers and AI Agents for Self-Remediation at Azure High Performance Computing
Software Engineer @Microsoft AI
Session
The New Architecture for Generative Search and Recommendations
RecSys and Search Lead @DoorDash,
Session
With Great Tooling Comes Great Responsibilities
Senior Director of Engineering @Datadog, 15+ Years in the Data and AI Industry
Why senior engineers trust QCon
What QCon AI attendees say
Senior engineers, architects and engineering leaders on what they took back from QCon AI New York.
I came in with a question: how much of what's presented at an AI conference is real, and how much is demo with more lights and noise than substance? And today there was a lot of substance, more than I expected.
The strongest message I brought was not about models. It was about execution, going beyond the hype and understanding how companies run AI at full scale.
Being surrounded by engineers and AI practitioners building real, scalable systems gave me a fresh perspective on how thoughtful design, trade-offs, and long-term impact shape good software. What stood out most was the community and the honesty.
Bring the people who own the decisions
Production AI takes a team.
What each role takes back:
type SoftwareArchitects
patterns for where an LLM's judgment belongs and where deterministic code takes over
type StaffPlusEngineers
what it takes to turn a demo agent into a system that survives a failed run
type MLMLOpsEngineers
eval designs that say ship or hold
type PlatformEngineers
how other platform teams handle model access, eval pipelines, and inference cost
type SecurityEngineers
identity, least privilege, and kill switches for tool-using agents
type EngineeringLeaders
adoption metrics tied to delivery and quality
Teams that attend together hear the same thinking firsthand and settle the build-or-wait debates faster.
Make the case
Convince your manager
You go back with patterns ready to adopt, costly mistakes you can now avoid, and a way to de-risk technical investments before building them. The pre-written templates make the case for you.
Convince your manager
Extend your stay
Coming in early or staying on?
The hotel works as a weekend base. Manhattan is five minutes away for evenings and shows, the waterfront promenade is there for a morning run, and Newport Centre is next door.
Bring the team
Group rates
Three or more people from the same company get $50 off each ticket, rising to $125 off for groups of 16 or more. Email info@newyork.qcon.ai with your group size and we’ll send you a code. Group bookings close November 27.
See group ratesTwo days with the engineers running this in production
You’ll come back with patterns ready to adopt, costly mistakes you can now avoid, and a way to de-risk what your team builds next. Current pricing ends September 8th, $1,535, after which it goes to $1,620.