AI Engineer New York has 137 sessions on the schedule and up to five running at any given moment. Choices have to be made. Here is a look at the sessions and evenings you might build your day around.
Today, Monday: Workshop Day
Pick the workshop that matches a problem already on your desk and stay for the whole thing. The Claude Managed Agents Workshop with CJ Avilla and Harrison Stall opens Sutton at 9:00. Teams still figuring out how to measure agent quality belong in Turing, where Laurie Voss kicks off with Evaluations with Phoenix 101.
A big opportunity is at 1:15 in Sutton. Nick Nisi and Zack Proser’s Beyond “Done”: Building Verification Loops for AI Agents takes on the question hanging over the rest of the week. How does a team trust what an agent hands back? The Expo opens at 4:00, and the welcome reception runs from 5:00 to 7:00.
Tuesday: Trust, Money, and Agents That Pay
Show up early for keynotes. Max Kanat-Alexander asks “Does Code Quality Even Matter?” at 9:54. Aparna Dhinakaran follows at 10:12 with “What does an AI engineer do?” Two big questions, both before 10:30. Freddy Lecue follows at 10:40 with the Wells Fargo foundation model that handles fraud detection at scale.
Later, the evals room has a great morning on the schedule. “Your Financial Agent Passed Every Eval. Can You Defend Its Decision?” at 11:30 and “Lies, Damned Lies, and Evals” at 11:55 both ask how much a good benchmark score is worth once regulators start asking questions.
Anyone tracking agentic payments should catch Jan Curn’s “Agents can pay. So why don’t they?” (12:20, Shannon) and Ishween Kaur’s “Your Agent Just Paid for Nothing (6 Attacks on x402 Payments)” (2:55, Turing). Banks and card networks spent the last few weeks pushing agent payments past the pilot stage.
For everyone security-minded, the Intent Based Auth panel at 11:30 in Simons puts Dick Hardt, Allie Howe, Ian Livingstone, and Michael Davis on one stage to sort out who an agent is and what it gets to touch.
Tuesday night will be fun! Table Stakes, a ping-pong happy hour from Arize, Modal, Google DeepMind, and more, runs from 5:30 to 8:30. Keycard, Braintrust, and Socket bring demos and drinks to the Elsie Rooftop. Optiver’s Think Fast! trivia night at M Social goes until 10:00. RSVPs required across the board.
Wednesday: Can AI Do the Job?
Day Two makes room for the skeptics. At 11:05 in Shannon, Ryan Stevens explains why giving a finance agent more context made it worse. Over in McCarthy, “Can AI run Goldman Sachs?” (11:30) and “Agents Can Rewrite Compilers. Why Can’t They Pick Stocks?” (12:20) take the hype straight at finance’s hardest problems. Stick around McCarthy at 11:55 for Maty Bohacek’s “Two Ways to Rob an AI-Native Bank.” You won’t want to miss it.
Thinking about careers? Catch Addy Osmani and Manish Kapur on “Who verifies the software factory?” (11:30, Sutton), then Laurie Voss on “The Rise of the Product Engineer” (12:20, Shannon). Runway CEO Cristóbal Valenzuela closes the keynote stage at 5:06 with “Everything will be Simulated”. Big title. Good closer.
Thursday: Still Going
Don’t miss the final few events: Prior Labs and Mistral host The Next Frontier of AI Agents in Midtown Thursday night while Sonar runs an afternoon session at Convene on Madison Avenue about building an agentic software factory.
Times and rooms can still move. Check the live schedule before committing.