An event dedicated to exploring all things AI Engineering!

Event partners: WorkOS & LlamaIndex

​Agenda

​​​​​🕒 5:30 pm – 6:00 pmGathering and Opening Remarks

🎤 Pramanya Guda, Ops & Community at Daytona

​​​​​​​🕒 6:00 pm – 6:15 pmTalk "Convince your coworkers to actually use your app"

🎤 Greg Sabo, Engineering Manager at WorkOS

​​​​​​​Outline:

An AI agent can build an internal tool in minutes. Then a coworker asks to use it. Whose credentials does it run with? Which company data can it access? What happens when someone outside the team opens the link? A working app leaves all of these questions unanswered.

This talk explores what it takes to turn AI-generated code into software a team can actually use: authentication, permissions, credentials, and deployment. I’ll demo the workflow with Alto at WorkOS, taking a small internal tool from an agent’s workspace to a deployed app with controlled access, then making a change live. The focus is on the infrastructure that lets teams keep building quickly as their apps gain real users and access to company systems.

​🕒 6:15 pm – 6:30 pmTalk "Your Agent's Slowest Tool Is Its Mouse"​

🎤 Muhammad Annas Hashmi, DevRel at Daytona

​​​​​​​Outline:

Every 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.

​🕒 6:30 pm – 6:45 pmTalk "Why Your Agent Can't Read Your Docs"

🎤 Yong Park, Member of Technical Staff of LlamaIndex

​​​​​​​Outline:

Every document your agent reads was built for a human eye. A table is a table because of where the lines fall. A column break is obvious because you can see the gutter. Strip the layout out and you get a wall of numbers with no header, two columns spliced into one sentence, and a chart that simply isn't there. The model answers anyway and that's what makes it expensive.This talk builds the failure map for document ingestion. Where the information actually gets lost, why the same pipeline works on one vendor's invoices and breaks on the next, and how to tell a parsing problem from a retrieval problem before you spend a week tuning the wrong layer. The fixes: preserve structure instead of flattening to text, treat layout as signal, and check the parse output directly instead of judging it through the answers. We'll show exactly  how we're solving this with LlamaParse.

​🕒 6:45 pm – 7:00 pmTalk "Give Your AI Agents a Map: Context Graphs for Safer, Smarter Code Changes"

🎤 Aniruddha Shevade, Staff Engineer at Postman

​​​​​​​Outline:

Most AI coding agents have no idea what a change might break downstream — they're reasoning about code without a map of the system around it. I'll share how we built a live graph of services, APIs, and dependencies that agents can query directly, and what it did for their accuracy and speed once they could finally see the blast radius before touching anything.

​​​​​​​​​​​​​​​🕒 7:00 pm - 8:00 pm

​​Networking

About event

This 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.