Phase 6: Prompt Engineering & GenAI Feature Design · 50 min · Multi-step agents · Autonomy levels · Human-in-the-loop design

Designing AI Agent Products

The question isn't whether your agent can take the action. It's what happens the one time it takes the wrong one.

Hiring signal: Multi-step agent products are the fastest-growing category of AI feature, and interviewers now routinely ask candidates to design one on the spot. The signal they're testing: does the candidate default to maximum autonomy because it demos well, or do they deliberately choose an autonomy level and an oversight mechanism matched to the action's reversibility and stakes? The second answer is what separates a PM who has shipped an agent from one who has only used one.

What you will learn

Explain multi-step agent architecture (plan, act, observe, repeat) at a level sufficient for product design decisions
Apply an autonomy-level framework to decide when an agent should act independently versus ask permission
Design escalation and approval UX for actions with real-world consequences
Identify the specific product risks introduced by giving an agent multiple sequential tool calls instead of one

The Problem

A team ships an AI travel-booking agent: tell it your trip constraints, it searches flights, picks the best option, and books it — fully autonomously, because the demo where it "just handles everything end to end" tested extremely well with stakeholders. Two weeks after launch, it books a flight with a departure time that technically satisfies the user's stated constraint ("morning") but leaves at 5:40 AM, which is not what any reasonable person meant by morning, and the ticket is non-refundable. Nobody approved that specific booking before it happened. The team's response is "we'll add better prompting for what counts as morning" — a fix aimed at the wrong layer. The actual gap: the team never deliberately chose an autonomy level for an irreversible, financially consequential action. It defaulted to full autonomy because that's what the demo showcased, not because anyone decided a fully unattended booking flow was the right amount of oversight for this specific action.

Designing an agent product means making that choice deliberately, action by action, not once for the whole feature.

Multi-Step Agent Architecture, at a Product Level

An agent, as distinct from a single prompt-response call, executes a loop: it plans a next step, acts (often via a tool call from Lesson 2), observes the result, and decides whether to continue, adjust the plan, or stop — repeating across multiple steps toward a goal, rather than producing one output for one input. The travel-booking agent's loop might look like: search flights -> evaluate options against constraints -> select one -> book it -> confirm to the user, each step depending on the result of the last.

The product risk this introduces that a single-call feature doesn't have: errors can compound across steps, and a wrong decision at step 2 (a training-data-adjacent misreading of "morning") can lead to an irreversible action at step 4 with no human ever having seen the full chain before it executed. This is the central product design problem of agents: as the number of autonomous steps between "user's stated goal" and "real-world consequence" grows, so does the value of an explicit checkpoint somewhere in that chain.

Unlock the full lesson

You've read the first 2 sections. The rest of this lesson covers Autonomy Levels: A Framework PMs Can Actually Use, Designing the Escalation and Approval UX, Build It, What to Practice — plus a hands-on lab, quiz, and project artifact.

Create a free account to unlock Phase 0 and Phase 1 of every course — no credit card.

Key terms in this lesson

Agent