Build AI Agents that Never Sleep

Build AI Agents that Never Sleep

Build durable Node.js agents with Inngest, event-driven execution, human approvals, and reliable recovery.

Build an incident-response agent that investigates a simulated service, takes action, waits for human approval, and resumes after failures. Learn how to put the harness in control with durable execution, events, safe retries, and observable state.

What You Will Master
Understand how background execution differs from a chat interface and when an agent needs a durable lifecycle.
Build a Node.js agent harness that observes current state, validates model-selected actions, and verifies completion.
Use Inngest to checkpoint model calls and tool execution so runs can resume after app restarts.
Suspend runs until events, timers, or human decisions arrive, then reassess the current state.
Require approval for disruptive actions and handle rejection, expiry, and changed conditions before execution.
Make retries safe with action idempotency, timeouts, run limits, and cancellation.
Use a local event simulator and Inngest traces to reproduce failures and explain what a run did.
Leave with a working incident-response agent and a reference architecture you can adapt for your own background workflows.

Prerequisites
Comfortable with modern JavaScript or TypeScript and basic Node.js development.
Able to run a local Node.js project, install dependencies with npm, and work from the terminal.
Familiarity with async/await, APIs, and basic server concepts.
Basic understanding of LLM APIs or prior use of an AI SDK is helpful, but not required.
Bring a laptop with Node.js LTS, npm, Git, and an editor already installed.
An LLM API key is recommended for the hands-on exercises.

Who is this for?
This workshop is for developers who already have some JavaScript or TypeScript experience and want to move beyond chat-based AI demos into real agent systems. It is especially useful for full-stack engineers, backend engineers, and technical founders building automations, internal tools, or product features where work needs to continue asynchronously in the background. Prior agent experience is helpful but not required.

BLDAGTAYTGHADNSEAELPRTGTJYTAVEFRFT

you must be registered member to see linkes Register Now