# AI for Developers: from issue to reviewed change

> Establish a dependable AI-assisted development workflow from issue to tested, reviewed change.

Developers practise how to give coding tools the right repository context, plan changes, inspect generated work, run tests and leave evidence for reviewers. The focus is team reliability, not faster typing.

## What this program changes in practice

Coding assistants can produce a convincing change before they understand the repository, the reason behind the issue or the tests that protect the system. That is why the workshop treats AI-assisted development as a team operating practice rather than a collection of shortcuts. Developers learn to provide useful context, require a plan, inspect the diff, run the right tests and leave evidence that makes the eventual review easier rather than more uncertain.

The session is not a fixed sequence of demonstrations. The facilitator works with the team on Prepare repository context, Issue to plan, Plan to change, using GitHub Copilot, Codex & coding agents, Agent Design Canvas, 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 Repository instruction template, Agent-ready development workflow, Test-evidence 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.

![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_

![Physical method cards make the discussion and review steps visible. Innovation Time Lausanne × AI Workshop · UNIL · May 2026.](https://aiworkshop.ch/images/evidence/university-ai-workshop-agent-design-method-cards-lausanne.webp)

_Physical method cards make the discussion and review steps visible · Innovation Time Lausanne × AI Workshop · UNIL · 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_

![The facilitator reviews a participant’s work directly on the laptop. Innovation Time Lausanne × AI Workshop · UNIL · May 2026.](https://aiworkshop.ch/images/evidence/university-ai-workshop-george-mentoring-student-agent-design-lausanne.webp)

_The facilitator reviews a participant’s work directly on the laptop · Innovation Time Lausanne × AI Workshop · UNIL · May 2026_

## Program facts

- Recommended format: Core workshop · 4–6 hours
- Alternative formats: Focused workshop · 4 hours, Optional follow-up clinic · 60–90 minutes
- 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: Software engineers, technical leads, platform teams and product engineers using or evaluating coding assistants and agents.
- Reviewed: 2026-07-10

## Tools participants use

- **GitHub Copilot, Codex & coding agents:** Move from issue to plan, change, tests and review inside the team’s approved development environment.
- **Agent Design Canvas:** Define the job, sources, tools, permissions, decisions and human checkpoints before building an agent.
- **Your approved AI tools:** Exercises adapt to the systems, licences and data boundaries your organisation has approved.

## Outcomes

- Give coding tools useful repository context
- Move from issue to explicit implementation plan
- Require tests and review evidence from agent work
- Agree team boundaries, permissions and standards

## Practical syllabus

### 1. Prepare repository context

Create instructions, architecture notes and constraints the tool can follow.

**Working output:** Repository instruction template

### 2. Issue to plan

Turn an ambiguous request into a reviewable implementation plan.

**Working output:** Agent-ready development workflow

### 3. Plan to change

Make focused edits, inspect diffs and keep the developer in control.

**Working output:** Test-evidence checklist

### 4. Tests, security and review

Require evidence, test failure paths and examine security-sensitive changes.

**Working output:** Team standard and pilot backlog

### 5. Team operating standard

Define approved tools, permissions, review rules and a pilot backlog.

**Working output:** Repository instruction template

## What the team takes away

- Repository instruction template
- Agent-ready development workflow
- Test-evidence checklist
- Team standard and pilot backlog

## 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 AI for Developers workshop?

Establish a dependable AI-assisted development workflow from issue to tested, reviewed change. The practical outcomes are: Give coding tools useful repository context; Move from issue to explicit implementation plan; Require tests and review evidence from agent work; Agree team boundaries, permissions and standards.

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

Software engineers, technical leads, platform teams and product engineers using or evaluating coding assistants and agents.

### Which tools will participants use?

The practical stack includes GitHub Copilot, Codex & coding agents, Agent Design Canvas, 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, Optional follow-up clinic · 60–90 minutes. 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 Repository instruction template, Agent-ready development workflow, Test-evidence checklist, Team standard and pilot backlog, digital resources and a concise facilitator summary.

---

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