## Course Library

Browse and manage your learning content

### Total Courses

42

+8

8 added this quarter

Across all departments

### Active Learners

1,247

+18%

Growing steadily

Across all courses

### Avg Rating

4.7

+0.2

Highest this year

From learner feedback

### Completion Rate

78%

+5%

Best quarter yet

Across all programs

### Practice

#### Prompting Fundamentals

Write prompts that ship. Output schemas, role framing, few-shot vs chain-of-thought. Every lesson is graded by an AI evaluator on a hidden test set.

6h14 lessons  
4.9(412)  
2,840 enrolled  
78%  
Published

#### Evaluating AI Output

Build golden sets, write rubrics, run regression tests. Learn what good evals look like and ship one for your own agent.

8h12 lessons  
4.8(287)  
1,620 enrolled  
45%  
Published

#### RAG in Practice

Chunking, embeddings, retrieval evaluation. Build a real RAG pipeline against a noisy corpus and measure recall.

10h16 lessons  
4.9(356)  
2,210 enrolled  
22%  
Published

#### Agents 101

Tool use, planning loops, multi-step reasoning. Build an agent, then break it. Live grading on conversation transcripts.

12h18 lessons  
4.8(298)  
1,890 enrolled  
60%  
Published

### Tool Use & MCP

Wire AI to real systems via Model Context Protocol. Build MCP servers, consume them from agents, debug tool-call failures.

7h11 lessons  
4.7(184)  
1,240 enrolled  
90%  
Published

#### Shipping AI Features

From prototype to production: cost controls, latency budgets, observability, prompt versioning, regression gates.

14h20 lessons  
4.9(412)  
3,120 enrolled  
100%  
Completed

#### Red-Teaming AI Systems

Adversarial prompting, jailbreaks, prompt injection. Try to break sample agents — your attacks are scored by severity.

5h9 lessons  
4.8(156)  
890 enrolled  
15%  
Draft

#### Voice AI & Real-Time

STT, TTS, turn-taking, latency. Build a voice agent end-to-end and measure conversational quality with AI graders.

9h13 lessons  
4.7(98)  
412 enrolled  
0%  
Draft

Invalid domain for site key.