Weave
YourPath
Weave
YourPath
Applied AI Engineering
Course Material
Module 1
: AI Foundations and Responsible Use
Module 2
: Prompt Systems and Structured Output
Module 3
: Python for AI and Model APIs
Module 4
: Production Wrapper: retries, cost, logging
Module 5
: Tool Calling and Multi-Step Workflows
Module 6
: RAG I: chunk, embed, retrieve, cite
Module 7
: RAG II: rerank, filter, rewrite, evaluate
Module 8
: Agents: loops, tools, stop conditions
Module 9
: Evaluation: golden sets, baselines, regression
Module 10
: Deploy and Capstone
Projects
1
Your responsible-use charter
2
Mini-build 1: reliable prompt system
3
Mini-build 2: validated streaming model client
4
Mini-build 3: resilient AI service
5
Tool-using workflow
6
Major project, part 1: grounded knowledge assistant
7
Retrieval evaluation report
8
Supervised agent workflow
9
Evaluation harness and report
10
Capstone: build, deploy, defend in writing
Grades
Notes
Course Info
Go back to Student Dashboard
Evaluation: golden sets, baselines, regression
42 min of videos left
Evaluation you can defend
Video · 16 min
Start
LLM-as-judge: when it is legitimate
Video · 14 min
Regression testing in CI
Video · 12 min
Build and label your golden set
Lab · 80 min
Wire the harness into CI
Lab · 70 min
Evaluation harness and report
Project · 88 min
Evaluation check
Quiz · 20 min
