← back
The Demo I Wish I'd Had: OpenAI's Agents SDK... serverless! - Brook Riggio
Takeaway
A production-friendly agent stack today is Next.js + Vercel + Inngest + OpenAI Agents SDK Python, glued by serverless functions and event-driven orchestration.
Summary
- Brook Riggio (Thrive.com) presents his preferred zero-ops serverless stack for agentic apps: Next.js + Vercel for the client, OpenAI Agents SDK (Python) for agents, Inngest for orchestration, Vercel for hosting.
- Architecture: user hits Next.js app → Inngest event triggers Python serverless functions (Vercel auto-detects Python) running Agents SDK → results cached in Vercel blob storage → UI polls DB for completion.
- Why Inngest: event-triggered (no JSON state-machine docs), automatic retries, step-level observability, one-click Vercel integration; gives a local dev server for the orchestration layer.
- Why OpenAI Agents SDK: native tool calling, multi-agent handoffs, built-in tracing/eval hooks, model swap support, strong OpenAI backing.
- Demo app generates an AI newsletter at the intersection of user-provided topics; uses three local terminals (Python agents, Next.js, Inngest dev) and Vercel preview deployments for every push.
agentsserverlessopenai-agents-sdk
Original description
Deploying and orchestrating significant AI workflows on serverless platforms like Vercel presents unique infrastructure challenges, like managing time limits and persistent state, handling task failures, and achieving reliable execution. As an engineer exploring OpenAI's powerful new Agents SDK on Vercel, I initially struggled with fitting sizeable jobs within the limits of our serverless platform. In this highly practical, hands-on session, you'll experience the demo I wish I'd had—showing exactly how to use Inngest's native integration with Vercel to run OpenAI's Agents SDK for robust orchestration and execution of complex, long-running AI workflows. We'll cover practical solutions for retries, state preservation, and seamless orchestration within the constraints of Vercel's serverless platform. You'll leave this talk equipped with clear, actionable strategies for implementing production-ready AI infrastructure on Vercel, including essential best practices for monitoring, observability, and robust error handling. Whether you're building your first AI system or enhancing existing workflows, this demo-driven talk provides the tools and insights needed for resilient, scalable AI deployments on Vercel. Complete demo repo: https://github.com/brookr/serverless-agents Please fork this, build your own examples, and send a PR to link to your work!