Agents are particularly hard-to-debug software.

For one, and by design, AI models behave in non-deterministic ways. Even two identical prompts don’t always yield the same output.

But agents are also complex distributed systems. They involve multiple steps of computation across functions and sandboxes, touching dozens of API services that can go down, rate limit you, etc.

Nailing down observability out of the box for http://eve.dev on Vercel was a key priority for the team, and the feedback so far has been ↓

eve – The Agent Framework - Vercel

Source: https://vercel.com/eve

The framework for building agents

Like Next.js for web apps, but for agents. Markdown for instructions and skills, TypeScript for tools. Durable by default.

An agent is a directory

Define instructions and skills in markdown, tools in TypeScript, and deploy. The framework compiles the directory, wires up durable workflows, and connects channels.

Leverages all Vercel AI primitives

AI Gateway for model calls, Sandboxes, Workflows, and Connect. All critical agent infrastructure works out of the box, no gluing point solutions together.

Everything you need for production agents

Enterprise governance, observability, and sandboxed compute come standard. Focus on building, not infrastructure.

• Durable executionWorkflows survive crashes and restarts. Every step is checkpointed. Agents park when waiting, resume on the next message.
• Sandboxed computeAgents spin up isolated VMs on demand. File system access, bash execution, and code runs, all completely isolated.
• Multi-channel deliveryOne agent codebase deploys to web chat, Slack, API, cron, CLI, and custom apps.
• Human-in-the-loopTools that need confirmation trigger approval gates. Sessions park until resolved, then resume seamlessly.
• SubagentsDelegate specialized work to child agents with their own prompts, tools, and sandbox.
• EvaluationsDefine test suites with scoring rubrics. Run evals on every deployment and on a schedule.

Build your first agent today.

Vercel Developers (@vercel_dev): You can now trace and debug eve agent runs with Vercel Observability.

Inspect model and tool calls, runtime errors, and token usage in one place.