Long-Running AI Agents: Patterns for Agents That Run Hours

This course contains the use of artificial intelligence.

Building an AI agent that works for five minutes is easy. Building one that works for five hours, unattended, is a different problem.

Leave an agent running overnight and it breaks in predictable ways. Its context fills up and it starts mixing up customers. The server restarts at 2 AM and nobody knows whether that refund went through. It gets stuck in a loop and burns money until morning. It marks work as "done" when nothing was done. And sometimes it takes an action nobody can undo.

This course teaches the design patterns that prevent each of these failures. They are the same patterns behind today's coding agents, background agents and durable workflow engines, explained clearly enough that you can apply them in any stack.

One story, one night, one agent

The whole course follows Nightshift, an agent working the night shift at Pebblecart, a small online store with 600 support tickets left over from Black Friday. Nightshift has real tools: it looks up orders, reads the refund policy, emails customers and issues refunds.

The first night goes badly. Section by section, you give Nightshift the patterns it needs, and in the last lesson it finishes a full night: tickets resolved, risky refunds waiting for approval, hard cases handed to humans, and a sensible bill.

The 5 ways long-running agents break, and what you'll learn to fix them

• Forgetting: compaction, clearing tool results, just-in-time retrieval, sub-agents, progress files, structured work lists, goal anchoring.

• Dying: checkpoints, event logs and replay, idempotent tools, workflow engines, suspend and resume with webhooks, work queues with leases.

• Getting stuck: retries with backoff, loop detection, token and money budgets, stop conditions, circuit breakers and fallback models.

• Lying: verification with facts instead of the agent's word, evaluator–optimizer reviewers, overnight reconciliation.

• Acting recklessly: approval gates, async human approval, escalation, and defending against prompt injection in customer emails.

You'll also learn when multiple agents beat one, how to hand off work between agents, how to trace an 8-hour run, and how to cut the cost of a night's work.

What makes this course different

• Patterns, not a framework. Everything applies whether you use the Claude Agent SDK, LangGraph, Cloudflare Agents, Temporal, Inngest or your own loop. Each lesson ends with where the pattern already exists in popular platforms.

• Short, focused lessons. Every video is 3 to 6 minutes and teaches one pattern.

• Animated diagrams instead of slides. Every idea is drawn and animated step by step, so you can see the mechanism, not just hear about it.

• Pseudocode code cards. Each pattern ends with a short pseudocode card you can translate into any language. The harness grows lesson by lesson, with new lines highlighted.

• No setup, no repo to maintain. Watch on your phone, on the train, or between meetings.

Also included

• A scenario quiz at the end of every section, based on real incidents from Nightshift's nights

• A final assignment: design the harness for your own agent on one page

• Pattern cards (PDF): one card per pattern with the problem, diagram, pseudocode and trade-offs

• Pattern map (PDF): every pattern on one page, organized by failure mode

• Overnight checklist (PDF): what to check before you let an agent run unattended

By the end of this course, you'll be able to look at any agent, predict how it will fail on a long run, and choose the patterns that keep it on track.

Enroll now and give your agent a night shift it can survive.

This course is independent and is not affiliated with or endorsed by any of the companies or products mentioned. Pebblecart and Nightshift are fictional names created for this course.