Hardware-Accelerated Network Security for Line-Rate Cloud Performance

Tools like Lovable have made it possible for a non-technical founder to ship a working prototype in a night. Getting that prototype in front of paying customers, handling their data safely, and keeping it running when something breaks is a different problem. Karen Forde, founder of Bridge the Gapp, spends her working week reviewing codebases that founders built with AI tools and no engineering team. She will walk through what she finds, what it costs to fix, and the handful of decisions you can make early that keep a prototype on a path to production. Hosted by The AI Collective's Dublin chapter and Baseline, this is the follow-on to Pilots & Prototypes. If you built something at Part 1, bring it. If you didn't make Part 1, you're still welcome. Who this is for: Founders and operators who have built a prototype with AI tools and are wondering what comes next, along with anyone about to sell, pilot, or raise on something they built themselves. No engineering background needed! Schedule: 6:00 p.m. - Doors open and networking 6:30 p.m. - Event kick off, session led by Karen Forde 7:15 p.m. - Q&A with Karen and non-technical founder 7:30 p.m. - Build time! 8:30 p.m. - Demos and sharing 9:00 p.m. - Close What to bring: A laptop and your prototype, if you have one. Questions about your own build are welcome in the clinic. About the speaker: Karen Forde is the founder of Bridge the Gapp, a software consultancy working with early-stage founders on code and architecture review, technical direction, and moving AI-built products towards production. Please be advised: Unfortunately, space is very limited at these community events and we can not always accept everyone we would like to. If you are not accepted to this event, please keep applying! We appreciate your application tremendously and we are looking forward to seeing you at a future event very soon! The AI Collective is a global non-profit building the human layer for the AI era. We unite 200,000+ leaders, builders, and

AI sits on both sides of the observability equation. On one side, your AgentCore apps and agents are production systems nobody quite knows how to debug: non-deterministic and unwilling to explain themselves. On the other, those same models are being pointed back at your telemetry as an on-call assistant that reads traces faster than any human can. We're taking both seriously, and you'll build on both. After a short framing talk, we run two hands-on sessions: one instrumenting an AgentCore agent with OpenTelemetry's GenAI semantic conventions, one wiring a model up to live telemetry so it can work a real incident. We circle back at the end to compare each approach. Bring a laptop. Food, drinks, and accounts provided. Agenda: Doors open Welcome & Housekeeping (5min) KickOff: AI for Observability & Observability 4 AI (25min) Track A: Observability for AI (30-45min) Track B: AI for Observability (30-45min) Drinks & Networking