Go beyond single prompts into planning loops, tool registries, memory, and evaluation for reliable agents.
Includes practical lessons, exercises, and a clear next step after you enroll.
About this course
Curriculum
Lessons are listed in order. Each one has a goal, a walkthrough, practice, and a short check before you continue.
- 01Agent architectures that scalePick a loop you can explain: plan, act, observe, stop.
- 02Tool calling and guardrailsLet the model choose tools without giving it the keys to production.
- 03Memory and long-running tasksStore only what the next step needs, then pick the work back up.
- 04Recovering from tool and model failuresTurn errors into retries, fallbacks, or a clean handoff to a human.
- 05Evaluating agent reliabilityMeasure task success, not how clever the trace looks.
- 06Putting an agent into a real workflowPlace the loop next to tickets, inboxes, or cron — with an owner.
- 07Workshop: a complete pass on a real taskCombine the earlier lessons into one working example you can keep.
- 08Quality bar, common mistakes, and a 30-day planLock in a checklist so the skill survives after the course ends.
- 09Measure results so you know the work is actually betterAdd a simple evaluation so quality and cost are not guesswork.
- 10Ship it: handoff, monitoring, and the next projectPut the workflow where other people can use it without you in the room.