Module 4 of 4Lesson 2 of 3~15 min
Building a dedicated assistant, then handing tasks to an agent
Some tasks come back every week and deserve better than a prompt pasted in by hand. This lesson helps you design a reliable assistant for one of them, then judge when an agent that acts on its own makes sense, and what human oversight to keep over the work it does for you.
Lesson objective
By the end of this lesson, you will be able to configure an assistant dedicated to a recurring task, test it on real cases, and decide whether a task justifies an agent, with which human approval points.
Topics covered
- custom AI assistant
- AI agents
- automating recurring tasks
- human in the loop
Where it fits
Set up an assistant, work with diligence
How do you stop starting from scratch, hand more work to AI and stay accountable for the result?
Lessons in this module
- Stop repeating yourself with standing instructions and projects
- Building a dedicated assistant, then handing tasks to an agent (this lesson)
- Working with diligence
What you will learn in the course
This lesson is part of the course Prompting for Product Managers: delegate, describe, verify
- Decide, for a task in your product cycle, whether to hand it to AI, in which mode (automation, augmentation, agent), and what you keep.
- Explain how an LLM behaves (prediction, dated knowledge, working memory, instruction following) to anticipate its mistakes and pick the right fix.
- Write a prompt that describes the deliverable, the process and the quality bar, with context, delimited data and examples when needed.
- Evaluate an AI output (content, process, behavior) against explicit criteria, then improve it through targeted iterations.
- Produce PM deliverables with AI (feedback synthesis, persona, interview guide, user stories) from real data, and check that they are faithful to it.
- Configure standing instructions and a dedicated assistant for a recurring task, test it on real cases, and decide when to move to an agent.
- Apply diligence rules (shared data, transparency, accountability) before using or circulating work produced with AI.
Related courses
- Build reliable Claude Skills for your product workAdvanced · ~2 hr 30 min
- Choosing and using AI tools at workAll levels · ~1 hr 40 min
- Understand what LLMs do well, and where they failAll levels · ~2 hr