AI-assisted full stack development

Objectives

• Write a specification and an implementation plan that can be used both by a code assistant and by a human reviewer
• Produce with an assistant, review and test an API backend with a database and authentication, correcting errors and invented dependencies
• Produce and adjust a web interface connected to that API, usable on a computer and on a phone
• Generate, check and complete automated tests up to a set target coverage, and audit the AI-produced code for security (injections, secrets, permissions) and technical debt
• Deploy the application through a containerised continuous integration pipeline and write the documentation that allows a third party to take it over

Audience

Junior to experienced developers, software engineers, IT teams that develop in-house; technical teams taking over an application built by a provider.

Prerequisites

Program in at least one language (Python or JavaScript), use Git and understand how an HTTP request works. Checked by an online placement test.

Technical prerequisites

• One laptop per participant, 16 GB of memory recommended, with Git, Docker, Node.js, Python 3 and a code editor installed before the first day (procedure supplied with the invitation).
• Access to code assistants (Claude Code and an assistant built into the editor, in their current-edition versions), API keys and a cloud deployment environment supplied by Yolea, credits included.
• Training Git repository.
• For remote attendance, a stable connection of at least 10 Mbit/s, microphone and camera.

Skills covered

• Specification for assisted development
• Driving a code assistant (generation, iteration, agent mode)
• Critical review and testing of generated code
• Basic application security
• Deployment and documentation

Programme

• 20% input, 80% supervised building.
• One project per participant, from specification to deployment, on a brief inspired by company situations (customer portal with order tracking, ticket management tool, field data collection application).
• Technology stack of the current edition: FastAPI or Django, PostgreSQL, React or Next, Docker, GitHub Actions.
• Cycle required for every feature: specify, generate, review, test, validate.
• Daily code reviews in pairs.
• Materials supplied: reference repository, library of development prompts, checklist for reviewing generated code, documentation template, glossary.
• Personal action plan.
• Follow-up session after three weeks.

Format

35 hours, 5 consecutive days of 7 hours, or 3 + 2 days a week apart with coaching between the modules. In person recommended, hybrid possible; in-company or open enrolment; 8 to 12 participants.

Assessment

Beforehand, an online placement test. During the course, a daily check quiz and code review. At the end, a demonstration of the application to a Yolea panel, assessed against a grid (features delivered, tests, security, deployment, ability to explain the code), an immediate feedback evaluation and a named certificate of completion. After three weeks, a follow-up session.

The last exercise is an action plan: three real tasks that you leave ready to equip with tools.