Agents & APIs Los Angeles Developer Meetup

Join us for another awesome Agents and APIs Developer Meetup brought to you by Postman!
You'll have a great time learning, connecting with the dev community, and enjoying delicious food!
Speakers
Talia Kohan, Staff Developer Advocate, Postman
Beyond Code Generation: Building Context-Aware Engineering Agents
Most AI coding tools can generate code. Few can answer a more important question: what else needs to change?
In modern systems, a single API change can impact specifications, collections, backend services, frontend applications, tests, CI/CD pipelines, databases, documentation, and infrastructure. Experienced engineers know that implementing the change is often the easy part. Understanding its downstream impact—and updating every dependent system correctly—is where the real work begins.
This talk explores how autonomous agents can move beyond code generation by leveraging a Context Graph built from the artifacts engineering teams already maintain: API specifications, collections, tests, environments, source code, and runtime dependencies. Rather than operating on individual files in isolation, these agents can reason about relationships across an entire system.

Koi Chavez, Field Engineering, Vercel
The API's Logic Lives in a Sentence
Most API business logic lives in code, validation rules, conditional flows, edge case handling, all buried in functions that only the engineer who wrote them can safely change. In this demo, we'll hit a live API with an edge case it gets wrong. Then, instead of touching code, we'll edit one sentence of plain English describing the new rule, redeploy, and call it again. Same endpoint, same URL, new behavior. It's a look at what happens when you move business logic out of code and into natural language: the speed you gain, the assumptions it breaks and why agents are finally reliable enough to make that shift practical.

Yaroslav Borets, Product Manager, Render
The Hard Part Is Moving: The Evolution of Agent Architectures
Over the past year, we’ve spent a lot of time talking with teams building AI agents, from coding assistants and research tools to enterprise automation. One thing has become pretty clear. As models have improved, the hard part has shifted. The harness and surrounding architecture are increasingly where top teams differentiate.
In this talk, I’ll walk through how agent architectures have evolved over the past year and why we’re seeing the industry converge on the same set of building blocks: filesystems, durable execution, long-lived sessions, and eventually multi-agent systems. We’ll look at what changed in the models, why those changes matter, and how they are driving the next generation of AI architectures. I’ll also share where frameworks (Flue, OpenAI, Anthropic Agent SDK, Eve), and others seem to be heading.
If you’re building AI agents today or trying to understand where the ecosystem is headed, I hope you’ll leave with a clearer picture of the emerging architectural patterns and what they mean for the next generation of AI applications.

Matthew Colozzo, Software Engineer, Astro AI

Space is limited.

💬 Keep the Conversation Going
Join us in the Postman Discord server to gain access to resources shared by the speakers.
❤️ Accessibility
Please let us know about any accessibility needs at least three weeks before the event. We will do our best to accommodate.
Legal Stuff
By signing up you agree: Postman, Inc. can send me updates and news about its products and services. I can unsubscribe anytime using the link in an email or by contacting Postman.