Help me design what the user sees while an agent works.

THE AGENT: [what it does]
WHO USES IT: [role, how busy, how technical]
TYPICAL DURATION: [seconds]
TYPICAL STEP COUNT: [easy case and hard case]
WHAT IT PRODUCES: [the output]

Please design:
1. What appears on screen during the run. Write the actual text for a typical case, step by step, as the user would see it appear.
2. The result view, what's shown by default versus what's behind a 'show detail' control
3. What happens when the user clicks stop halfway. What do they see, and what do they keep?
4. What the user sees when the agent gives up because it hit a cap. Write that message, it should be useful, not an error.
5. What the first-ever run should look like differently from the hundredth
6. Three things that would damage trust irreversibly on a first use, so I can make sure none of them can happen

Agentic AI and MCP for Product Managers

Module 1What 'Agentic' Actually Means

Module 2How an Agent Actually Works

Module 3MCP: What It Is and Why You Should Care

Module 4Designing the Tool Layer

Module 5Permissions and the Human in the Loop

Module 6Evaluating Agents

Module 7Cost, Latency and Unpredictability

Module 8Designing What the User Sees

Module 9Risk and Blast Radius

Module 10When an Agent Is the Wrong Answer

Module 11Final Project: Design One Real Agent End to End

Module 12Appendix: The Prompt Library

Copy This Prompt - Designing the Agent Experience