

Daytona AI Builders - SF, September 2026
โAn event dedicated to exploring all things AI Engineering!
โEvent partners: WorkOS & LlamaIndex
โโAgenda
โโโโโโ๐ 5:30 pm โ 5:35 pm
Welcome and Opening Remarks
โ๐ค Borna Perak, GTM & Partnerships @ Daytona
โโโโโโโโ๐ 5:35 pm โ 5:50 pm
Talk "Your Agent's Slowest Tool Is Its Mouse"โ
โ๐ค Muhammad Annas Hashmi, DevRel at Daytona
โโโโโโโโOutline:
โEvery click a GUI agent makes costs a full screenshot and a model round trip, and it only lands if the layout stayed where the model last saw it. Chain a task out of clicks and you have bought seconds of waiting and a context window full of pixels for work a shell one-liner could have done. Screenshots are heavy. Text is light. And a click sequence is the most fragile program ever written. No variables, no error handling, and the only retry is asking the model again.
This talk builds the cost model of computer use. Where the waiting actually comes from, why pixel agents break when nothing is wrong, and the levers that fix it: read structure (a DOM, an accessibility tree) instead of rendering it to an image first, write code instead of emitting one click at a time, and cache what worked so the second run costs nothing. I'll then follow up with a demo of what we're doing at Daytona to address these.
โโ๐ 5:50 pm โ 6:05 pm
Talk "TBA"
โ๐ค Speaker from WorkOS
โโโโโโโโOutline:
โTBA
โโ๐ 6:05 pm โ 6:20 pm
Talk "TBA"
โ๐ค Speaker from LlamaIndex
โโโโโโโโOutline:
โTBA
โโ๐ 6:20 pm โ 6:30 pm
Talk "The AI Builderโs Survival Guide: Bridging Engineering, UX, and Stakeholder Buy-In"
โ๐ค Varsha Kori, Senior UX Designer at Amazon
โโโโโโโโOutline:
โBuilding powerful AI models and agentic workflows is only half the battle. The real hurdle is turning complex, non-deterministic backends into intuitive products that users trust and stakeholders support. In this talk, Iโll share a practical survival guide based on my experience at Amazon, helping AI engineers and product creators navigate the messy realities of shipping modern AI.
โFrom handling unpredictable outputs to aligning technical capabilities with core business goals, Iโll outline actionable frameworks to bridge the gap between deep technical execution and seamless user adoption.
โKey takeaways include:
โ- Translating AI to Value: Frame complex technical architecture into tangible business impact to secure executive buy-in.
โ- Designing for Uncertainty: Build user trust and effective feedback loops within non-deterministic agent interactions.
โ- Frictionless Engineering and UX Collaboration: Bridge the divide between technical sandboxes and end-user interfaces without slowing down development momentum.
โ- Whether you're developing autonomous agents, LLM-powered features, or developer tooling, you'll leave with a clear blueprint to ensure your AI breakthroughs deliver real-world product success.
โโ๐ 6:30 pm โ 6:40 pm
Talk "TBA"
โ๐ค Speaker TBA
โโโโโโโโOutline:
โTBA
โโ๐ 6:40 pm โ 6:50 pm
Talk "TBA"
โ๐ค Speaker TBA
โโโโโโโโOutline:
โTBA
โโโโโโโโโโโโโโโโ๐ 6:50 pm - 8:00 pm
โโโNetworking
โWith pizzas and beverages
โAbout event
โThis is dynamic gathering for AI enthusiasts, innovators, and professionals to collaborate, share ideas, and explore the latest advancements in artificial intelligence. Whether you're building AI products, researching cutting-edge algorithms, or simply passionate about the field, join us to connect, learn, and drive the future of AI forward.