Human Agency Over AI Agents: From Product Sense to Agent Sense
Mike Wheeler
Agentic Workflow Design & AI Educator
AI agents are here. Most workflows aren't ready.
AI agents are entering real workflows faster than organizations can safely adapt. New tools appear weekly, but the underlying work has not been redesigned. Teams experiment without clear rules for delegation, escalation, or accountability, often recognizing risk only after agents break trust, quality, or customer experience.
This course helps you move from experimentation to intentional design. You will redesign a real workflow you own or influence and make explicit decisions about what AI agents should automate, augment, or escalate to humans. You will leave with a stakeholder-ready workflow blueprint, including documented workflows, delegation and escalation rules, and criteria for reviewing agent performance over time.
The course is built around the Agent Sense Framework, a human judgment framework for designing AI agents as part of real workflows. Agent Sense extends Product Sense into the agentic era by focusing on accountability, escalation, and decision-making so your designs hold up as tools change. Through exercises, discussion, and hands-on use of the Agent Design Blueprint Tool, you apply the Agent Sense Framework to your own workflows.
What you’ll learn
Design AI-enabled workflows with clear human accountability and escalation using the Agent Sense Framework.
Apply Jobs-to-Be-Done thinking to find high-leverage, low-risk agent use cases
Distinguish automation, augmentation, and escalation in real workflows
Make defensible delegation decisions in multi-agent scenarios
Define clear ownership when work is shared between humans and agents
Make accountability visible across agent-enabled workflows
Design workflows where responsibility never becomes ambiguous
Design triggers that move work to humans at the right moments
Preserve context across agent-to-human and agent-to-agent handoffs
Develop escalation designs using production-style agent workflows
Assess whether agent behavior still aligns with original workflow intent
Identify failure modes in coordination and handoffs
Improve workflows iteratively without rebuilding from scratch
Translate agent behavior, escalation, and risk into stakeholder language
Defend design choices to leadership, legal, and delivery teams
Communicate why certain decisions must remain human
Build a complete blueprint covering intent, roles, escalation, and guardrails
Document human decision points across agent workflows
Leave with an artifact that can be shared, implemented, and evolved
Learn directly from Mike
Mike Wheeler
AI educator and O’Reilly author focused on accountable agent workflow design
Who this course is for
Operations and transformation leaders responsible for workflows who need a defensible way to introduce AI agents with accountability.
Senior ICs and team leaders designing complex workflows who need clarity on what AI agents should automate, augment, or escalate.
Consultants and advisors helping organizations adopt AI who need tool-agnostic designs they can explain, defend, and evolve over time.
Prerequisites
Experience owning or influencing reaI workflows
You should be familiar with how work is done today and have visibility into the decisions, handoffs, and outcomes involved.
Comfort making decisions with accountability
This course assumes you are used to making or advising on decisions that affect outcomes, risk, or other people’s work.
Interest in adapting real work for AI agent support
You do not need prior AI or agent experience, but you should want to thoughtfully adapt existing workflows for agent support.
What's included
Live sessions
Learn directly from Mike Wheeler in a real-time, interactive format.
Live agent workflow design studios
Interactive live sessions where we design real workflows together. We analyze tradeoffs, surface design tensions, and make defensible decisions for work you own or influence.
Guided workflow design exercises
Structured exercises that help you adapt existing workflows for AI agent support. You will define delegation boundaries, escalation points, and human accountability through facilitated drills.
Agent Sense Framework
A durable decision framework for determining what agents should automate, augment, or escalate to humans. Designed to remain useful as tools, vendors, and platforms change.
Agent Design Blueprint Tool
Hands-on use of the Agent Design Blueprint Tool to create your stakeholder-ready workflow blueprint. Tool access is provided during the course, with read-only access for 90 days after.
Capstone workflow blueprint
A complete, review-ready workflow blueprint covering intent, roles, escalation paths, guardrails, and human decision points. Designed for use inside your organization.
Real-world agent use cases
Examples from operations, service, sales, and cross-functional workflows showing how agentic patterns translate into designs organizations can govern.
Live discussion and Q&A
Dedicated time to ask questions, challenge assumptions, and explore edge cases. These discussions surface common failure modes and alternative approaches across contexts.
Session Recordings
Access to session recordings for 12 months to revisit key discussions and reinforce your thinking as you apply concepts in real work.
Private cohort community
A private cohort space to share progress, compare approaches, and learn from how peers reason through similar workflow challenges across industries.
Certificate of Completion and professional recognition
A certificate of completion issued upon finishing the course and capstone workflow blueprint. For participants who complete the capstone to a high standard, I offer optional LinkedIn skill endorsements reflecting demonstrated Agent Sense.
Maven Guarantee
This course is backed by the Maven Guarantee. Students are eligible for a full refund up until the halfway point of the course.
Course syllabus
4 live sessions • 4 lessons • 3 projects
Week 1
Feb
4
Human Agency and Delegation Decisions
Workflow Selection and Scope
Week 2
Feb
13
Optional: Office Hours: Escalation and Accountability
Fri 2/138:00 PM—9:00 PM (UTC)Optional
Feb
11
Escalation, Failure, and Accountability
Escalation and Accountability Design
Office Hours (optional)
Schedule
Live sessions
2 hrs / week
Live, interactive 90+ minute Zoom sessions held on Wednesdays at 2:00 PM Central Time (3 PM Eastern Time / Noon Pacific Time). Each session is designed for discussion and application, with time reserved for questions and live scenario analysis.
Wed, Feb 4
8:00 PM—9:30 PM (UTC)
Wed, Feb 11
8:00 PM—9:30 PM (UTC)
Wed, Feb 18
8:00 PM—9:30 PM (UTC)
Fri, Feb 13
8:00 PM—9:00 PM (UTC)
Projects
2-4 hrs / week
Time spent extending your Agent Design Blueprint after each live session. Projects are due Fridays at 5:00 PM Central Time and build progressively toward a final, stakeholder-ready blueprint.
Async content
1 hr / week
Short text lessons and optional replay viewing that reinforce live discussions and prepare you to complete each week’s project.
Frequently asked questions
$2,500
USD