# Agentic AI Workshop: design a safe, testable pilot

> Choose one important workflow and leave with a safe, testable agent pilot.

Your team moves beyond agent demos. Participants define the job, sources, permissions, decisions and human checkpoints for an agent that fits a real workflow.

## What this program changes in practice

Agentic AI becomes useful when a team stops asking what an agent could do and starts defining one job properly. That means agreeing the trigger, the information the agent may use, the actions it may take, the decisions it must never make alone and the person who remains accountable. This workshop gives the team enough structure to have that conversation together before anyone invests in a platform, integration or ambitious automation project.

The session is not a fixed sequence of demonstrations. The facilitator works with the team on Choose the workflow, Define the agent’s job, Connect sources and tools, using Agent Design Canvas, ChatGPT, Your approved AI tools when those systems are approved and available. Participants compare first results, make missing context visible and improve the work together. They learn not only which request works, but why an output is reliable enough to move into the next working step.

The value should not end when people leave the room. Exercises therefore produce concrete outputs such as Agent Design Canvas, Permission and approval map, Failure-test checklist. They give colleagues a traceable starting point, show where human review is still required and make the next pilot smaller and more realistic. Optional follow-up work can build on those artefacts instead of beginning again with another general introduction.

## What an AI Workshop looks like

These are photographs from real AI Workshop sessions in Switzerland—not generated illustrations. The captions preserve the actual session context, even when an image is used to show a wider part of the learning experience.

![The facilitator explains how a bounded workflow can become an AI agent. Agentic AI workshop · Lausanne · May 2026.](https://aiworkshop.ch/images/evidence/agentic-ai-training-lausanne-agent-workflow-ladder.webp)

_The facilitator explains how a bounded workflow can become an AI agent · Agentic AI workshop · Lausanne · May 2026_

![A participant completes the Agent Design Canvas by hand. Agentic AI workshop · Lausanne · May 2026.](https://aiworkshop.ch/images/evidence/agentic-ai-workshop-lausanne-agent-design-canvas.webp)

_A participant completes the Agent Design Canvas by hand · Agentic AI workshop · Lausanne · May 2026_

![A participant tests an AI-assisted workflow on a laptop. Agentic AI workshop · Lausanne · May 2026.](https://aiworkshop.ch/images/evidence/agentic-ai-workshop-lausanne-hands-on-coding.webp)

_A participant tests an AI-assisted workflow on a laptop · Agentic AI workshop · Lausanne · May 2026_

![The facilitator makes tools, connections and human checkpoints explicit. Agentic AI workshop · Lausanne · May 2026.](https://aiworkshop.ch/images/evidence/agentic-ai-workshop-lausanne-mcp-architecture.webp)

_The facilitator makes tools, connections and human checkpoints explicit · Agentic AI workshop · Lausanne · May 2026_

## Program facts

- Recommended format: Core workshop · 4–6 hours
- Alternative formats: Focused workshop · 4 hours
- Delivery: On-site / in person, online, or hybrid
- Languages: Delivered in English, French or German
- Prerequisites: No technical prerequisite; exercises use approved tools and non-sensitive examples.
- Audience: Business, product, operations, innovation and technical teams ready to examine one multi-step workflow together.
- Reviewed: 2026-07-10

## Tools participants use

- **Agent Design Canvas:** Define the job, sources, tools, permissions, decisions and human checkpoints before building an agent.
- **ChatGPT:** Draft, analyse, research and turn recurring work into reusable team instructions.
- **Your approved AI tools:** Exercises adapt to the systems, licences and data boundaries your organisation has approved.

## Outcomes

- Select an agent opportunity worth testing
- Separate agent work from human decisions
- Design permissions and review points
- Plan a small pilot with clear tests

## Practical syllabus

### 1. Choose the workflow

Map the current work, friction and decision owner.

**Working output:** Agent Design Canvas

### 2. Define the agent’s job

Set the goal, boundaries, inputs and expected output.

**Working output:** Permission and approval map

### 3. Connect sources and tools

Decide what the agent may read, use and change.

**Working output:** Failure-test checklist

### 4. Design human control

Add approvals, escalation and a visible source trail.

**Working output:** Pilot brief with owner and next step

### 5. Test before pilot

Create failure cases, success measures and a first pilot plan.

**Working output:** Agent Design Canvas

## What the team takes away

- Agent Design Canvas
- Permission and approval map
- Failure-test checklist
- Pilot brief with owner and next step

## Prepared delivery

- Sponsor alignment call
- Short participant questionnaire
- Examples adapted to your work
- Facilitated live practice
- Digital resources
- Concise facilitator summary

## Frequently asked questions

### What will our team achieve in the Agentic AI workshop?

Choose one important workflow and leave with a safe, testable agent pilot. The practical outcomes are: Select an agent opportunity worth testing; Separate agent work from human decisions; Design permissions and review points; Plan a small pilot with clear tests.

### Who is the Agentic AI workshop designed for?

Business, product, operations, innovation and technical teams ready to examine one multi-step workflow together.

### Which tools will participants use?

The practical stack includes Agent Design Canvas, ChatGPT, Your approved AI tools. Exercises are adapted to the licences and systems your organisation has approved.

### How long is the workshop and how is it delivered?

The recommended format is Core workshop · 4–6 hours. Every core workshop is designed to stay within four to six hours; alternatives include Focused workshop · 4 hours. Choose an in-person session at your organisation or an agreed venue, a fully online workshop, or a hybrid format. Delivery is available in English, French or German.

### What preparation is required?

No technical prerequisite is required. We hold a short sponsor alignment call and participant questionnaire, then adapt examples to approved tools and non-sensitive work.

### What does the team take away?

The working package includes Agent Design Canvas, Permission and approval map, Failure-test checklist, Pilot brief with owner and next step, digital resources and a concise facilitator summary.

---

Provider: AI Workshop Switzerland  
Canonical page: https://aiworkshop.ch/workshops/agentic-ai/  
Contact: hello@aiworkshop.ch