The key insight from Vercel's internal agent work: giving an agent a file system didn't just add storage, it changed how the agent behaved. It started following through on long tasks, staying on track, and building on its own prior work. That's what this workshop builds toward.

@nicoalbanese10  walks through AI SDK v6 from scratch: a tool loop agent, provider-executed web search, end-to-end type safety, and Vercel's new persistent named sandboxes. The agent gets a bash tool, a memories.md file it reads and writes, and instructions that make it generate Python scripts for repeatable tasks and store them for later. By the end, it's an agent that accumulates tools and context across sessions without any manual memory management.

Speaker info:
- https://x.com/nicoalbanese10
- https://www.linkedin.com/in/nicoalbanese/
- https://github.com/nicoalbanese

AI Engineer

A live workshop walkthrough by Nico Albanese from Vercel demonstrating how to build an AI agent with a persistent computer/sandbox using the Vercel AI SDK. The session covers setting up a Next.js app with the AI SDK's ToolLoopAgent, adding web search via provider-executed tools, integrating Vercel Sandbox (beta) for persistent file system access, and implementing agent memory via a markdown file stored in the sandbox. Key concepts include the three types of tools (custom, provider-defined, provider-executed), call options and runtime context for passing sandbox instances to tools, context window management strategies, and how a file-system-backed agent dramatically improves task completion and reduces hallucination. The talk concludes with a demo of a production coding agent system using sub-agents, durable workflows, and a 91% cache token read ratio.

Give Your Agent a Computer — Nico Albanese, Vercel