i2Business — Consulting & Training : Intelligence to your business
Home/Training/Agentic AI for developers — Level 1
i2Business training session
3 days · 21hIA-280In-houseTFP-eligible (Tunisia)

Agentic AI for developers — Level 1

RAG, MCP servers and tool-using agents.

Level 1 is the entry point to the agentic AI track for developers. In three days, the team builds a complete application chain on the OpenAI APIs: an AI-assisted development method applied to a real repository, a RAG pipeline backed by a vector database, an MCP server built and hardened, then an agent that uses both building blocks.

The chain is then hardened against prompt injection, measured with an evaluation set and instrumented for context consumption. A single common thread links all the workshops: the team does not build isolated mock-ups, but one application that grows richer every day.

The concepts (MCP protocol, chunking, reranking, evaluation) remain provider-agnostic: each workshop comes with its adaptation layer and the equivalent code for a second provider (Claude).

(+216) 36 361 552
Agentic AI for developers — Level 1
Duration3 days · 21 h, 9 modules and 9 workshops
Schedule08h30 – 16h50, 20-minute coffee break and 1-hour lunch each day
AudienceJavaScript / TypeScript and C# / ASP.NET Core developers, application development teams, tech leads and software architects
FormatIn-house, in person; each participant works on their own machine
PrerequisitesJS/TS or C#, Git and Docker basics. No machine learning knowledge required
ValidationNamed certificate; each workshop ends with a demo by the participant on their own machine
TFP funding: how does it work?

Detailed syllabus

3 days, 9 modules, 10 workshops

Each day combines core concepts in the morning with hands-on practice on your own use cases in the afternoon.

Day 1 — AI-assisted development and RAG foundations

08h30 – 09h00Welcome
Welcome and scoping
  • Objectives, delivery modes, presentation of the 3-day common thread.
  • Environment checks: Node.js, .NET, Docker, Git, OpenAI API keys.
  • Deliverable: environments validated on every machine.
09h00 – 09h30Module 1
AI-assisted development method
  • Scoping the need, context passed to the model, short iterations.
  • Systematic review of generated code, limits and pitfalls.
09h30 – 10h15Module 2
OpenAI API: surface and first calls
  • Responses and Chat Completions, embeddings, function calling, structured outputs, streaming.
  • Token counting, error codes and rate limits.
  • Deliverable: notebook run by each participant and API summary sheet.
10h15 – 10h35Break
Coffee break
10h35 – 12h20Workshop 1
Vibe coding on a real repository
  • Analysis of an existing Node.js or ASP.NET Core repository.
  • Generating missing tests, fixing bugs, refactoring a module, running the test suite.
  • Deliverable: Git branch with tests and fix, annotated prompt log, test run report.
12h20 – 13h20Break
Lunch
13h20 – 14h05Module 3
Anatomy of a RAG
  • Ingestion chain, chunking strategies, embeddings, indexing, retrieval.
  • Prompt construction, source attribution, causes of hallucinations.
14h05 – 15h35Workshop 2
RAG pipeline
  • Ingesting a document corpus, chunking, computing embeddings, indexing.
  • Semantic search and generation of an answer that cites its sources.
  • Deliverable: runnable RAG service, set of 10 reference questions with sourced answers.
15h35 – 16h35Workshop 3
Vector database (and comparative demo)
  • Qdrant in a container: collection schema, metadata, filters, response time measurement.
  • Comparative demo: pgvector, SQL Server 2025 (VECTOR type), Pinecone, Elasticsearch / OpenSearch.
  • Deliverable: containerized vector database connected to the RAG, completed selection grid.
16h35 – 16h50Wrap-up
Debrief and handover of the day's repositories

Technologies & platforms

The tools you'll work with

Each platform is used live during the workshops, on your own use cases. No technical prerequisites required.

OpenAI APIModelsResponses, embeddings, function calling, structured outputs, streaming, Batch and Evals.
QdrantVector databaseIn a local container, connected to the RAG pipeline; compared with pgvector, SQL Server 2025, Pinecone and OpenSearch.
MCPTool protocolServer built in Node.js or .NET, documented, tested and secured.
Node.js / ASP.NET CoreApplication stackParticipant's choice, on a test repository provided with the course.
DockerEnvironmentContainerized vector database, SQL Server and demo services.

Your trainer

Portrait de Mohamed Kais Khenine, fondateur et formateur i2Business
Mohamed Kais Khenine, MBA
Senior Consultant & Trainer in AI, Digital Transformation & Digital Marketing

The course is led by a consultant who designs and deploys AI agents connected to our clients' business systems every day. Demos are run live, on production tools, under real-world security, cost and compliance constraints.

OpenAI API & RAGMCP & SkillsAI agentsClaude CodeSecurity of AI applications

Funding

This course is eligible for TFP funding

Our training firm is state-approved in Tunisia (approval no. 11 1823 19), which means your company can have its training costs refunded through the TFP (Tunisia's Professional Training Tax) if it is eligible for the related tax credit.

1Eligibility checkWe confirm with you that your company is subject to the TFP (Tunisia's Professional Training Tax) and that the program qualifies as an eligible expense.
2File submissionPreparation of the advance or refund application: detailed program, quote, schedule and provisional list of participants.
3Course deliveryDaily attendance sign-in, learning assessment and named certificates compliant with the scheme's requirements.
4Documentation and refundDelivery of the closing file — invoice, attendance sheets, certificates — for the refund application.
What we provide
  • Detailed training program, hour by hour
  • Named quote and compliant invoice
  • Attendance sheets signed per half-day
  • Learning assessment at start and end of the course
  • Individual certificates of completion
Questions about eligibility? Call us directly.(+216) 36 361 552

Go further

Related courses

See the full catalog
Become an AI-Augmented Traffic Manager — Level 1PractitionerIA-293Become an AI-Augmented Traffic Manager — Level 1One profession, four acquisition channels managed with AI: Meta (Facebook and Instagram), Google Ads, LinkedIn Ads and ChatGPT Ads, with a validation exam for each subject.50 hoursIn-house or public session, in personAgentic AI for digital marketing — Level 1PractitionerIA-292Agentic AI for digital marketing — Level 1From chat to action: KPIs, SEO, Google Ads, GA4 and Meta Ads managed with Claude, its Skills, its MCP connectors and a cross-channel marketing agent.3 days · 18hIn-house, in personAgentic AI for sales teamsPractitionerIA-291Agentic AI for sales teamsFrom chat to action: automate prospecting, meeting preparation, proposals, CRM and sales management with Claude, its Skills and its agents.3 days · 18hIn-house, in person

Book a session

Public session or in-house training at your premises, tailored to your processes. We'll get back to you within 24 business hours with a proposal and the TFP paperwork.

(+216) 36 361 552