Integrating AI agents into your development practices
A day on your own repository, from the agent's first run to a written merge request. Participants leave with a versioned context file, a change shipped with its tests, and a delegation matrix that states where humans stay in control.
This training is designed for:
The skeptical developer
They tried the agent on a real task, got sloppy code back, and want a way of working that holds up day to day.
The lead who has to set the rules
Their team already uses agents, each person in their own way, and they need to set review rules before that code goes to production.
The freelancer reviewing alone
They ship solo and want to go faster without letting through what a reviewer would have caught.
Integrating AI agents into your development practices
Learning objectives
The learning objectives of this training can be assessed. By the end of the session, each participant is able to:
- Install and configure Claude Code on a code repository, in the terminal and from your development environment, setting tool permissions
- Write a versioned project context file describing the repository's architecture, conventions and verification commands
- Carry out a code change with an agent, from approved plan to reviewed diff, isolating the work on a dedicated branch
- Have the agent write and run automated tests covering a fix, and check that they fail for the right reason before the fix
- Review, correct and document generated code with an explicit 6-point review checklist
- Package a recurring sequence of tasks into a custom command the team can reuse
- Apply the rules on confidentiality, secrets management, dependency licensing and traceability that govern code submitted to an AI tool
- Write up a delegation matrix that sets the mandatory human checkpoints, and a 30-day action plan with tracking indicators
Audience and prerequisites
Audience. Developers, whatever their main programming language. Tech leads, architects and team managers who need to set the rules for AI agent use in their organization. DevOps, data and test engineers who automate coding and operations tasks. Freelancers and technical contractors who want to systematize their development workflow.
Prerequisites. The training assumes regular hands-on software development in the trainee's usual programming language. No prior AI knowledge is needed: the necessary concepts are covered in the session. From the first hour, the trainee works on a code repository they know well and have their employer's or client's permission to use. Daily use of a programming language and a code editor (VS Code, JetBrains or equivalent). Regular use of git: branches, commits, merge requests. Knowledge of your project's build process and test suite.
Each participant's actual level is checked before the session with a placement questionnaire, which is used to adjust the outline.
Program
The full outline, sequence by sequence, is in the detailed program you receive before registering.
Want this training for your team?
Answer 3 questions and your estimate appears. We call you back within 48 hours with the quote, the detailed program and possible dates.
Teaching methods and resources
The training combines demonstrations with commentary, guided workshops and hands-on work on the participants' real cases. Theory is limited to what you need to put things into practice.
- A practitioner trainer who works on the subjects taught
- Course materials for each participant
- Each participant works on their own computer, with their own files
- Environment set up in advance and tested before the session
In person
The training takes place at the client's premises. The client provides a room with a projector or screen, an internet connection and a computer for each participant.
Remote
The training runs as a live virtual classroom, in a group with the trainer, on a fixed schedule. Participants interact by voice, screen sharing and chat, in both directions and throughout the session. Each participant's connection is logged and serves as the attendance record. Technical support is available by email and phone for the whole session, and a connection test is offered ahead of the day.
Hybrid
A single session can bring together on-site and remote participants. The trainer leads from the in-person venue, and remote participants follow in the virtual classroom with the same individual support and the same deliverables.
Assessment and certification
- Placement questionnaire before the training starts
- Continuous assessment through the exercises completed during the session
- Final assessment of learning against the objectives listed above
- Satisfaction questionnaire at the end of the session, then again a few weeks later
The training leads to an end-of-training certificate stating the objectives and the assessment results, and to a certificate of completion sent to the funder where applicable.
Official title in the training program: « Intégrer les agents IA dans ses pratiques de développement : générer, relire, tester et documenter avec Claude Code » (Integrating AI agents into your development practices: generating, reviewing, testing and documenting with Claude Code). Page updated on August 31, 2026.
Free course to get started with Claude
Judge our teaching before you commit a budget.
- 1 hour 20 minutes of video in 5 short modules
- Installing Claude and setting up your workspace
- 6 ready-to-copy skills and starter files
- The privacy settings to apply from your first day
- A selection of 20 AI tools for marketing
The course videos and emails are in French.
Questions?
Accessibility · results · complaints
Our quality commitments, our results indicators and the adjustments available to people with disabilities are published on a dedicated page.