Artificial Intelligence
Applied AI Engineering
Ship an AI system a recruiter can actually open.
About this course
The technical track, and the one that puts ‘AI engineering’ on your CV with work behind it. In 60 self-paced hours you build an AI application that retrieves from your own documents, calls tools, is measured against a golden dataset, and lives at a public URL — with Weave beside you 24×7. Ten modules, three mini-builds, one major project, and a deployed capstone. Fully AI-assessed: there are no live human sessions at this tier.
What you'll learn
- Build prompt systems with validated structured output and a real test suite
- Call model APIs from Python with retries, streaming, secrets handling, and cost tracking
- Build and deploy a RAG assistant that cites its sources and refuses when it cannot ground an answer
- Measure your own system against a golden dataset and defend the numbers
Course content
60 hours · 71 lessons · 31 videos · 10 guided project activities · 9 quizzes · 10 projects
AI Foundations and Responsible Use
What a language model actually does12 min
The model landscape: hosted, open, and the trade14 min
Break three models on purpose60 min
Cost and latency benchmark60 min
Your responsible-use charter60 min
Foundations check34 min
Prompt Systems and Structured Output
From prompt to prompt system14 min
Structured output that parses every time14 min
Prompt injection and untrusted input12 min
Build a schema-validated extractor90 min
Write the test suite90 min
Mini-build 1: reliable prompt system120 min
Prompt systems check20 min
Python for AI and Model APIs
Project layout and dependency discipline14 min
Calling model APIs safely16 min
Streaming, async, and timeouts14 min
Typed responses and boundary validation12 min
Build a typed model client from scratch80 min
Add streaming and a timeout budget80 min
Secrets audit on your own repository90 min
Mini-build 2: validated streaming model client150 min
Python and APIs check24 min
Production Wrapper: retries, cost, logging
The failure taxonomy14 min
Retries done right14 min
Observability for AI systems12 min
Wrap your client: retries, breaker, cost ledger80 min
Chaos lab70 min
Mini-build 3: resilient AI service150 min
Production wrapper check20 min
Tool Calling and Multi-Step Workflows
Tool calling: the model as router14 min
Multi-step workflows that resume14 min
Deterministic versus model-decided control flow12 min
Give your service three real tools80 min
Build a resumable pipeline70 min
Tool-using workflow150 min
Tools and workflows check20 min
RAG I: chunk, embed, retrieve, cite
Why RAG — and when it is the wrong answer16 min
Chunking without destroying meaning16 min
Embeddings and vector search14 min
Citation and refusal14 min
Compare three chunking strategies80 min
Retrieval and generation with mandatory citations80 min
Force a refusal70 min
Major project, part 1: grounded knowledge assistant170 min
RAG foundations check20 min
RAG II: rerank, filter, rewrite, evaluate
Your retrieval is worse than you think14 min
Reranking, filtering, and hybrid search14 min
Query rewriting and multi-hop questions12 min
Build a 50-question evaluation set80 min
Add a reranker and measure80 min
Retrieval evaluation report140 min
Advanced retrieval check20 min
Agents: loops, tools, stop conditions
The agent loop, honestly16 min
Stop conditions and budgets14 min
What an agent must never do alone12 min
Build a coding agent under test80 min
Make it fail safely78 min
Supervised agent workflow140 min
Agents check20 min
Evaluation: golden sets, baselines, regression
Evaluation you can defend16 min
LLM-as-judge: when it is legitimate14 min
Regression testing in CI12 min
Build and label your golden set80 min
Wire the harness into CI70 min
Evaluation harness and report88 min
Evaluation check20 min
Deploy and Capstone
Deployment paths for AI apps16 min
Monitoring in production14 min
The README a hiring manager will read12 min
Deploy, break, and fix70 min
Capstone: build, deploy, defend in writing188 min