Any questions?
2IIA
2IIA Assistant
Hello!
I'm the 2IIA assistant.
What are you looking for?
Back to the catalogue PART 2 · UNIVERSITIES AND SCHOOLS

Computer science and data students

AI agents, RAG and MCP

Build an application that combines retrieval-augmented generation (RAG), an agent and tools connected through the MCP protocol, and learn how to evaluate it.

3 days (21 h)
duration
100 %
online, live
Open / in-house
your choice
On quotation
price
Course sheet

AI agents, RAG and MCP

Target role Computer science and data students Duration 3 days (21 h) Format online, virtual classroom Price on quotation

Learning objectives

By the end of the course, participants will be able to:

  • Explain how a language model, a RAG system and an agent work
  • Build a RAG pipeline: chunking, embeddings, vector database, retrieval and source citation
  • Design an agent that calls tools and chains several steps
  • Expose and use tools through the MCP protocol
  • Evaluate the quality, reliability and cost of a system

Audience

Students in computer science, data science or AI (master’s, engineering school).

Prerequisites

Programming in Python; basic knowledge of web APIs. Prior use of a language model is a plus.

Day-by-day programme

SessionContent
Day 1 morningLanguage models: how they work, APIs, system prompts, structured outputs
Day 1 afternoonRAG: chunking, embeddings, vector database, hybrid search, source citation
Day 2 morningEvaluating a RAG system: question sets, relevance and faithfulness measures, common errors
Day 2 afternoonAgents: tool calling, execution loop, memory, guardrails and human validation
Day 3 morningMCP: protocol principles, writing an MCP server, connecting it to a client
Day 3 afternoonProject: document assistant with an agent and MCP tools, demonstration and review
Practical details

How the course works

Duration and format

3 days (21 h). 100% online, in a live virtual classroom with the trainer, with hands-on workshops. A computer, a stable connection and a headset with microphone are all you need.

Open or in-house

Open sessions bring together participants from several organisations. In-house sessions are run for a single group, on the date you choose and with cases adapted to your work.

Assessment

Initial assessment, practical exercises, final project assessed on functionality, evaluation and documentation. A satisfaction questionnaire at the end of the course and a certificate of attendance for each participant.

Teaching resources

Notebooks and repositories provided, access to a language model API, course materials. Materials remain available to participants after the course.

Accessibility

The course is accessible to people with disabilities. Our disability officer, Roland Dehghan Kamaragi, reviews each request before enrolment and proposes the necessary adjustments. Contact us.

Price

On quotation, depending on the format (open or in-house) and the number of participants. This course is not eligible for the French CPF scheme.

See also : AI Agents & MCP · RAG & Pipelines

Interested in this course?

Tell us the format, the period and the number of participants: we will reply with a programme and a quotation.

2IIA logo