Coding Agents Lunch & Learn - Session 14 From Agent Demos to Production Reality

Join us for Session 14 of the Coding Agents Lunch & Learn, our weekly community series exploring the tools, workflows, frameworks, and real-world applications shaping the future of AI coding agents.

This week, we’re diving into what happens when agents move beyond demos and into production workflows.

We’ll kick things off with a behind-the-scenes case study from Port of Context, where CEO Patrick Kelly will unpack how their team built and evaluated a GTM agent using Goose X Code Mode. Expect a practical look into agent design, performance measurement, token usage, execution time, lessons learned, and what actually matters when evaluating autonomous systems in production. Patrick will also share how manually running this process inspired the creation of the Agent Voyager Project (AVP), an open public specification for agent observability.

We’ll also hear from Sahil Kathpal for a focused lightning talk on techniques and frameworks for running long autonomous agent sessions reliably, the kind of agent workflows that persist for 60–90 minutes and require robustness, persistence, and orchestration to succeed.

Whether you’re building coding agents, experimenting with autonomous workflows, or trying to understand what reliable agent systems look like in practice, this session is for you.