AI & ML Quick Path
  1. Call a modelAPI or local, structured output
  2. Add knowledgeEmbeddings and RAG
  3. Add actionsTools and agents with approval
  4. Make it trustworthyEvaluation, security, responsibility

Talking to models

  1. Calling an LLM from your application

    Call a language model from Python and C#, request structured JSON, validate it, handle failures, stream answers and control cost.

    Beginner75 minNeeds: How large language models work

  2. Prompt engineering that works in production

    Write clear prompts with roles, rules, delimiters, examples and output formats, keep prompts versioned, and test them with a small evaluation set.

    Beginner60 minNeeds: Calling an LLM from your application

Knowledge: embeddings and RAG

  1. Embeddings and vector search

    Explain embeddings, find similar text by cosine similarity, and store and search vectors in a vector database from Python and C#.

    Intermediate75 minNeeds: Calling an LLM from your application, Text and sequences: tokens, embeddings and RNNs

  2. RAG: answering from your own documents

    Build a retrieval-augmented generation (RAG) system that checks permissions, retrieves evidence, answers with citations, says "I don't know" when evidence is missing, and is measured with an evaluation set.

    Intermediate2 hNeeds: Embeddings and vector search, Prompt engineering that works in production

  3. Advanced RAG: chunking, hybrid search, re-ranking and evaluation

    Improve RAG quality with better chunking, hybrid keyword-plus-vector search, reciprocal rank fusion, re-ranking, query rewriting and metadata filters, and measure each change.

    Advanced1.5 hNeeds: RAG: answering from your own documents

Actions: tools and agents

  1. Tools and agents with human approval

    Let a model call tools safely, design an agent workflow with explicit state, permission checks, human approval, retries, idempotency and an audit trail, in Python and C#.

    Advanced2 hNeeds: Calling an LLM from your application, Prompt engineering that works in production

  2. AI frameworks and MCP: what to use in Python and .NET

    Know what LangChain, LangGraph, Microsoft.Extensions.AI, Semantic Kernel, Microsoft Agent Framework and the Model Context Protocol do, and when plain code is better.

    Intermediate60 minNeeds: Tools and agents with human approval

  3. Multimodal AI apps: images, documents and voice

    Send images and documents to vision-capable models, build image-and-text search, and add speech input and output to an application.

    Intermediate60 minNeeds: Calling an LLM from your application, Computer vision: classification, detection and segmentation, Speech and audio: recognition and text-to-speech

Quality and trust

  1. Evaluating AI applications

    Build an evaluation set, write automatic checks, use an LLM as a judge carefully, detect hallucinations, and compare versions with A/B tests.

    Intermediate75 minNeeds: RAG: answering from your own documents

  2. Security for AI applications

    Recognise the main risks to LLM applications (prompt injection, data leakage, excessive agency and others), apply layered defences, and redact personal data before it reaches a model.

    Advanced75 minNeeds: Tools and agents with human approval, RAG: answering from your own documents

  3. Responsible AI: fairness, privacy, transparency and oversight

    Measure fairness between groups, protect privacy, explain decisions, keep people in control, and document models with model cards and risk registers.

    Intermediate60 minNeeds: Measuring models honestly, Security for AI applications

Advanced: the whole picture

  1. "Generative AI and Agentic AI: the whole picture"

    Explain in simple words what generative AI and agentic AI are, how they differ and work together, and decide when a task needs one, the other, both, or neither.

    Advanced60 minNeeds: How large language models work, Calling an LLM from your application, Tools and agents with human approval