136 lines
4.1 KiB
Markdown
136 lines
4.1 KiB
Markdown
# Student Orientation Guide
|
|
|
|
Welcome to the Agentic Engineering Course. This guide tells you exactly what to do first.
|
|
|
|
---
|
|
|
|
## Step 1: Prerequisites Checklist
|
|
|
|
Before starting, ensure you have:
|
|
|
|
- [ ] **Python 3.12+** installed (`python --version`)
|
|
- [ ] **Git** installed (`git --version`)
|
|
- [ ] **A text editor** (VS Code recommended)
|
|
- [ ] **At least one API key** (see API Keys section below)
|
|
- [ ] **Terminal** (PowerShell on Windows, bash on Mac/Linux)
|
|
|
|
### Optional (install later when needed)
|
|
|
|
- [ ] **Claude Code CLI** — `npm install -g @anthropic/claude-code`
|
|
- [ ] **Pi Agent CLI** — `npm install -g pi-coding-agent`
|
|
- [ ] **OpenCode CLI** — `npm install -g @opencode/cli`
|
|
|
|
---
|
|
|
|
## Step 2: Course Structure
|
|
|
|
The course is organized into **8 modules** with **13 labs**:
|
|
|
|
```
|
|
course/
|
|
├── 00-CURRICULUM.md ← START HERE: Full lesson plan
|
|
├── M1-FOUNDATIONS.md ← START HERE: Module 1
|
|
├── M2-ARCHITECTURE.md
|
|
├── ... (M3 through M8)
|
|
├── labs/ ← Hands-on exercises
|
|
│ ├── L1-first-agent/
|
|
│ ├── L2-multi-tool/
|
|
│ └── ... (13 total)
|
|
└── FIELD-MANUAL.md ← Quick reference cheat sheet
|
|
```
|
|
|
|
### How Each Module Works
|
|
|
|
```
|
|
1. Read the module file (M1-FOUNDATIONS.md)
|
|
2. Complete the lab exercise (labs/L1-first-agent/)
|
|
3. Take the quiz (ASSESSMENTS.md)
|
|
4. Move to next module
|
|
```
|
|
|
|
---
|
|
|
|
## Step 3: Your First Lab
|
|
|
|
Navigate to `labs/L1-first-agent/` and open `starter.py`:
|
|
|
|
```bash
|
|
cd course/labs/L1-first-agent/
|
|
python starter.py data.txt "What is this file about?"
|
|
```
|
|
|
|
**Don't have an API key?** The mock LLM client handles this automatically. Your code runs the same way with or without a real API key.
|
|
|
|
### Lab Tips
|
|
|
|
- Each lab has `starter.py` (fill in the blanks) and `solution.py` (reference answer)
|
|
- Try the starter first. Look at the solution only when stuck
|
|
- The `reasoning` parameter on every tool call is not optional — it's a course requirement
|
|
- Always set `MAX_ITERATIONS` to prevent infinite loops
|
|
|
|
---
|
|
|
|
## Step 4: Install Skills (Optional)
|
|
|
|
After completing Module 3 (Security), install the skill kits:
|
|
|
|
```bash
|
|
# Windows
|
|
powershell -File install.ps1
|
|
|
|
# Mac/Linux
|
|
bash install.sh
|
|
|
|
# Single kit
|
|
bash install.sh security
|
|
```
|
|
|
|
---
|
|
|
|
## Step 5: Recommended Learning Path
|
|
|
|
| Order | Module | Time | Do This |
|
|
|-------|--------|------|---------|
|
|
| 1 | M1 Foundations | 4-6 hrs | Read + Lab 1 |
|
|
| 2 | M2 Architecture | 6-8 hrs | Read + Labs 2a, 2b |
|
|
| 3 | M3 Safety | 5-7 hrs | Read + Labs 3a, 3b |
|
|
| 4 | M4 Orchestration | 7-9 hrs | Read + Labs 4a, 4b |
|
|
| 5 | M5 Production | 5-7 hrs | Read + Labs 5a, 5b |
|
|
| 6 | M6 Economics | 4-6 hrs | Read + Labs 6a, 6b |
|
|
| 7 | M7 Advanced | 5-7 hrs | Read + Labs 7a, 7b |
|
|
| 8 | M8 Capstone | 8-12 hrs | Build your project |
|
|
|
|
---
|
|
|
|
## Common Pitfalls
|
|
|
|
| Problem | Solution |
|
|
|---------|----------|
|
|
| `ModuleNotFoundError: anthropic` | Run `pip install anthropic` or use mock LLM (automatic fallback) |
|
|
| Lab runs but produces no output | Check you called `run_agent()` at the end of the script |
|
|
| Tool loop never terminates | Check `MAX_ITERATIONS` is set. Default is 15. |
|
|
| Mock LLM returns "No input provided" | Check you're passing `messages` to `create()` not just `prompt` |
|
|
| YAML parse error in skills | Check indentation — YAML uses 2-space indents |
|
|
|
|
---
|
|
|
|
## Getting Help
|
|
|
|
- **Course content issues**: Check the module file first, then the solution file
|
|
- **Lab errors**: Run `python -c "from mock_llm import MockAnthropic; print('OK')"` from the labs directory
|
|
- **Concept questions**: Module files explain concepts. FIELD-MANUAL.md is the quick reference.
|
|
- **Still stuck**: The course README.md has a full file listing
|
|
|
|
---
|
|
|
|
## What You'll Learn
|
|
|
|
By the end of this course, you will be able to:
|
|
|
|
1. Build single-tool and multi-tool agents from scratch
|
|
2. Implement the 6-level security ladder (L0-L5) to protect your systems
|
|
3. Design multi-agent systems with teams, chains, and peer-to-peer communication
|
|
4. Deploy agents to production with CI/CD, observability, and rollback
|
|
5. Optimize costs using cascade routing and evaluate performance with pass@k
|
|
6. Build self-improving agents that experiment and learn
|