UdemyADVANCEDDifficulty: ADVANCED

Production AI Engineering: RAG, Agents, Evals & MCP

The engineering around the model

4.9480 students14h16 lessons

Python · LangGraph · Ragas · pgvector · MCP · Claude API · FastAPI

The gap this fills#

There is a great deal of material on prompting and very little on the engineering that makes a language-model system survive production: evaluation gates, budget control, replayable traces, and failure modes that are safe rather than confident.

Prerequisites#

Strong Python. You should have built at least one RAG prototype and been dissatisfied with it.

Curriculum

5 sections · 16 lessons

  1. Retrieval

    • Chunking strategies compared
    • Reranking
    • Hybrid search
    • Measuring retrieval alone
  2. Evaluation

    • Building a golden set
    • LLM-as-judge and its biases
    • Regression gates in CI
  3. Agents

    • State machines over loops
    • Budget caps and retry limits
    • Failing safely
  4. MCP

    • Why a tool protocol
    • Building a server
    • Security boundaries
  5. Operating it

    • Cost tiering
    • Tracing and replay
    • Rolling out a prompt change

Free material on this topic

AI Engineer Lab

Why Your RAG Evaluation Is Wrong

Most RAG evaluations measure the wrong thing, on the wrong data, with a judge that rewards the wrong behaviour. Here is what to measure instead.

IntermediateDifficulty: Intermediate3 min readPython · Ragas · OpenAI API
Video
AI Systems

RAG Evaluation Lab

Most RAG systems are tuned by vibes. This is a reproducible harness that measures retrieval and generation separately, so you can see which half is failing.

IntermediateDifficulty: Intermediate~12h buildPython · Ragas · DuckDB
Code
AI Systems

AI Research & Fact-Checking System

A research agent that decomposes a claim, gathers evidence from multiple sources, cross-checks agreement between them, and refuses to answer when the evidence is thin.

AdvancedDifficulty: Advanced~20h buildPython · LangGraph · Claude API
VideoCode
AI & LLMFree

AI Token Cost Calculator

Model input and output tokens, request volume and caching to project monthly cost across model tiers.

1,020 runs