Durable AI (October Edition)

Luma discover page Event Link Durable AI w/ Temporal & Kernel Join us for the next edition of the Durable AI Meetup series! This time on what happens to an agent between the first request and the last one. A long-running agent needs three things to make it through: it has to survive a crash, it has to keep working against the systems it acts on, and you have to be able to see what it did. Most stacks solve one of those and hope about the other two. ―――――――――― What's Happening: 🎤 Lightning talks & demos from teams building agents that run long and survive failure 🤝 Networking with engineers and founders shipping agents into production 🍽️ Food, drinks, and real technical conversations ―――――――――― Agenda: 5:30 PM – Doors open | Food, drinks, networking 6:00 PM – Introductions & Welcome 6:05 PM – Talks & demos • Temporal • Kernel • Oodle.ai 7:00 PM – Closing panel & Q&A 7:15 PM – Open networking w/ food and drinks 8:00 PM – Close More speakers announced soon. ―――――――――― Who Should Come: • Engineers building agents that take real actions on real systems • Developers working on auth, orchestration, or long-running workflows for agentic apps • Platform and infra engineers responsible for what agents do in production ―――――――――― About the Companies: Temporal - Durable Execution platform that ensures your AI agents and workflows survive failures, handle long-running operations, and reliably complete, even when things go wrong. Kernel - Kernel builds crazy-fast, open-source infrastructure for AI agents to use the Internet. Sandboxed cloud browsers in under 30ms, with managed auth, stealth mode, residential proxies, live and MP4 session replays, and a serverless app platform that co-locates your agent with its browser. SOC2- and HIPAA-compliant and trusted in production by 7,000+ teams across finance, healthcare, and AI research. Oodle.ai - Observability built for agents. AI can't debug what it can't see. With Oodle, agents debug applications, infrastructure, and other agents with full context. Teams use it to build self-improving agents and catch failures early. One platform for full-stack and agent observability, built on object storage and serverless compute so you can store everything, query anything, and run sub-second agentic queries at 80% lower cost. Today, Oodle processes 900M+ agent spans and 3PB+ of telemetry every month. Hosted by Temporal & Kernel 🚀 Want to speak at a future meetup? --> fill out the Speaker Interest Form 📧 location provided by event source: "500 Sansome St, San Francisco, CA 94111, USA" ―――――――――― SF Stuff To Do