# How do you show people what an AI agent is doing while it works?

Show 4 things. The plan before it starts, so people can stop it early. The step it is on, in plain words. What it is waiting for, and from whom. A log when it ends, with the rule behind each action. People trust what they can follow. A spinner asks them to guess.

By Surinder Thakur, AI Product Designer and Builder. Published 17 Nov 2026. Topic: [Trusting AI with money](https://www.surinder.design/work?type=trusting-ai-with-money).

## Why show the plan first?

Because a wrong plan is cheap to stop and costly to undo. 1 glance catches a wrong supplier or a wrong order.

For long or costly jobs, the plan waits for a yes. For routine ones, it just shows and runs.

## What should the progress say?

The step, in the words your team uses. Checking stock at the main warehouse, not running tool call 3.

Show the count too, like step 2 of 4. People relax when they can see the end.

## Why name what it is waiting for?

Because an agent that waits silently looks broken. Waiting for the owner to approve is clear, and tells people who to nudge.

Silence is where people start doing the work by hand again.

## What belongs in the log?

What it read, what it decided, which rule allowed each action, and what a person approved.

Keep it readable by the team, not only by engineers. The log is how a manager switches the agent on.

## In 1 picture

Plan, progress, waiting and log: what an agent should show while it works.

1. Plan shown: Stop it early if wrong
2. Step 2 of 4: In your team's words
3. Waiting for you: Who, and for what
4. Logged: Each action with its rule

People trust what they can follow.

## Next questions

- [How do you design an AI agent approval screen people actually read?](https://www.surinder.design/work/how-to-design-an-ai-agent-approval-screen): Show 4 things on 1 screen: the action, the exact amount, the reason, and the rule that stopped it.
- [What is agentic UX, and why does it matter?](https://www.surinder.design/work/what-is-agentic-ux): Agentic UX is design for software that acts on a person's behalf.
- [What happens when an AI agent fails halfway through a task?](https://www.surinder.design/work/when-an-ai-agent-fails-halfway): A well-built agent stops, keeps what it finished, and recovers in 1 of 3 ways.
- [How do you get customers to use a new AI agent?](https://www.surinder.design/work/how-to-onboard-customers-to-an-ai-agent): Say it is an AI in the first message. Show what it can do in 1 line, with an example.

## Questions that lead here

- [Why do users stop using AI features after the first week?](https://www.surinder.design/work/why-users-stop-using-ai-features): Because the first week runs on novelty, and novelty is not a job.
- [What does the EU AI Act mean for a company using AI agents?](https://www.surinder.design/work/what-the-eu-ai-act-means-for-ai-agents): An agent that talks to people in the EU must tell them it is an AI.

Page: https://www.surinder.design/work/how-to-show-what-an-ai-agent-is-doing
