←Back to Blog
Course · 17 chapters

Applied AI Engineering

Building agents and automation. A path from how LLMs actually work up to shipping safe, evaluated agentic systems, written for working programmers, with no machine-learning math.

Applied AI Engineering
01

Foundations: How LLMs Work

  1. 01

    Inside a Language Model

    What an LLM actually is: next-token prediction, tokens, embeddings, attention, and the context window.

    1 unit
    →
  2. 02

    How Models Generate Text

    Logits to probabilities, temperature and sampling, the prefill/decode phases, and why models hallucinate.

    Coming soon
02

Communicating with Models

  1. 03

    Prompt Engineering

    Message roles, few-shot examples, chain of thought, and decomposing a job into reusable prompts.

    Coming soon
  2. 04

    Structured Outputs & Function Calling

    Forcing machine-readable output, JSON Schema validation, and the function-calling seed every agent grows from.

    Coming soon
03

Giving Models Knowledge (RAG)

  1. 05

    RAG Fundamentals

    The knowledge-cutoff problem, chunking, vector stores, and similarity search.

    Coming soon
  2. 06

    Advanced Retrieval

    Hybrid search, reranking, metadata filtering, and query rewriting for a real retrieval pipeline.

    Coming soon
04

Giving Models Tools

  1. 07

    Tool Use & the Agentic Loop

    Tool schemas, the call→result→continue loop, routing, and orchestrating many tools.

    Coming soon
  2. 08

    MCP & Connectors

    The standardisation problem MCP solves, its architecture, connectors, and agent-to-agent communication.

    Coming soon
05

Building Single Agents

  1. 09

    Agent Architectures & Reasoning

    The moving parts of an agent, ReAct, plan-and-execute, and self-reflection loops.

    Coming soon
  2. 10

    Memory & Context Engineering

    Working vs long-term memory, compression, context engineering, and state persistence.

    Coming soon
06

Multi-Agent Systems

  1. 11

    Coordinating Multiple Agents

    When multi-agent is worth it, supervisor/worker patterns, handoffs, and orchestration plumbing.

    Coming soon
07

Reliability & Safety

  1. 12

    Guardrails & Security

    Input/output filtering, prompt injection, jailbreaking, least privilege, and sandboxing.

    Coming soon
  2. 13

    Reliability & Error Handling

    Human-in-the-loop approval, retries, fallbacks, circuit breakers, and mid-run recovery.

    Coming soon
08

Evaluation

  1. 14

    Evaluating Agents & LLMs

    Why there is rarely one right answer, eval harnesses, benchmarks, and LLM-as-judge.

    Coming soon
09

Production & Capstone

  1. 15

    Serving & Performance

    What a serving engine does, how it scales under load, and keeping cost under control.

    Coming soon
  2. 16

    Observability & Deployment

    Tracing an agent run, monitoring quality over time, and surviving long failure-prone runs.

    Coming soon
  3. 17

    Frameworks & Capstone

    The major toolkits and when to reach for each, then assembling everything into one shipped agent.

    Coming soon