Skip to content

AI Engineer Summit 2026

Oct 12–13, 2026Moscone West, San Francisco

Two days for the people building AI systems that have to work on Monday morning. Practitioner talks on evaluation, agents, retrieval, inference infrastructure and the product decisions in between — no keynote fluff, no vendor pitches.

Sessions1 - 3 of 12

Everything on the program. Search by session title or speaker, or narrow it down by track.

  • ProductTalk

    Cost modelling for inference-heavy products

    How to build a unit-economics model for an AI product before the invoice teaches you: per-request cost decomposition, the caching wins that matter, routing between model tiers, and how to talk about all of it with a finance team.

    Monday, October 12: 02:00 AM - 02:45 AMWorkshop Room

    Speaker

  • ProductTalk

    What users actually do with your AI feature

    Six months of session recordings, support tickets and telemetry from a shipped AI feature, and what they revealed: the prompts people really write, where they give up, the workarounds they invent, and the three changes that moved retention.

    Tuesday, October 13: 09:30 AM - 10:30 AMMain Stage

    Speakers

  • ProductPanel

    Closing panel: what we got wrong about agents

    Four practitioners compare notes on the agent architectures they abandoned, the assumptions that did not survive production, and what they would build differently today.

    Tuesday, October 13: 04:00 PM - 05:00 PMMain Stage

    Speakers