Design Agent Workflows With Clear Checkpoints

Hosted by Mike Wheeler

70 students

In this video

What you'll learn

Identify AI tasks that need human checkpoints first

Know which agent actions are safe to automate and which require human review before they create problems you'll own.

Ask 3 questions before giving AI autonomy

Use a simple framework to decide what agents can do alone, when they need approval, and who's accountable when wrong.

Stop treating AI like a senior employee

Avoid the #1 oversight mistake: giving agents responsibilities you'd never hand a new hire on their first day.

Use the Agent Design Blueprint tool live

Get hands-on with a structured tool that captures intent, escalation paths, and guardrails for any AI workflow.

Why this topic matters

Agents don't fail because they're not capable. They fail because no one defined when they should stop and ask. Without clear checkpoints, small errors compound into big problems, and you're the one explaining it to leadership. This session shows you how to design the decision points that keep agent workflows accountable and on track.

You'll learn from

Mike Wheeler

AI educator and O’Reilly author focused on accountable agent workflow design

I help organizations adopt AI responsibly by designing judgment, accountability, and real workflows before tools enter the picture. I have trained hundreds of thousands of professionals through O’Reilly, Salesforce, edX, and LinkedIn, and my work focuses on building agent-enabled systems that augment people rather than replace them.

As seen on