🔍 Career path

Agentic AI Tester & QA Engineer

Test, evaluate, and trace autonomous AI agent systems.

0 / 29 complete

24 labs · ~8.1h total

Become a specialist in verifying agentic systems. Learn to evaluate output correctness and
faithfulness, trace complex multi-agent execution graphs, and automate adversarial prompt
injection security testing.

Targets: Agentic AI QA Engineer / AI System Evaluator / LLM Tester / Red Teamer

🐧 Linux Administration Foundation

4 labs · ~2.1h · Open path →

Prerequisite foundations — skip if you already know this.

  1. 1. Command Line & Filesystem 🧪 Lab · 7 steps ○
  2. 2. Users, Permissions, Processes & Automation 🧪 Lab · 7 steps ○
  3. 3. Partitioning, Filesystems & LVM 🧪 Lab · 5 steps ○
  4. 4. Networked Filesystems with NFS 🧪 Lab · 5 steps ○
  5. 5. Linux Administration - Knowledge Check ❓ Quiz ○

🐳 Docker Foundation

7 labs · ~2.6h · Open path →

Prerequisite foundations — skip if you already know this.

  1. 1. Your First Container 🧪 Lab · 3 steps ○
  2. 2. Working with Docker Images 🧪 Lab · 5 steps ○
  3. 3. The Container Lifecycle 🧪 Lab · 5 steps ○
  4. 4. Building Docker Images 🧪 Lab · 5 steps ○
  5. 5. Container Networking 🧪 Lab · 4 steps ○
  6. 6. Volumes & Persistent Storage 🧪 Lab · 4 steps ○
  7. 7. Real-World Container Apps 🧪 Lab · 4 steps ○
  8. 8. Docker - Knowledge Check ❓ Quiz ○

🐍 Python for AI Foundation

3 labs · ~50 min · Open path →

Prerequisite foundations — skip if you already know this.

  1. 1. Python for Data Engineering 🧪 Lab · 3 steps ○
  2. 2. Python for AI Engineering 🧪 Lab · 3 steps ○
  3. 3. Python for Agent Engineering 🧪 Lab · 3 steps ○
  4. 4. Python for AI - Knowledge Check ❓ Quiz ○

🔍 Agentic AI Testing & Observability

9 labs · ~2.3h · Open path →
  1. 1. Evaluating Outputs with Ragas 🧪 Lab · 3 steps ○
  2. 2. Evaluating Tool-Use Reliability 🧪 Lab · 3 steps ○
  3. 3. Observability & Trace Graphs 🧪 Lab · 3 steps ○
  4. 4. Promptfoo Security Red Teaming 🧪 Lab · 3 steps ○
  5. 5. Agent Loop Detection & Chaos Testing 🧪 Lab · 3 steps ○
  6. 6. Multi-Agent Protocols 🧪 Lab · 3 steps ○
  7. 7. Chaos & Self-Healing Agents 🧪 Lab · 3 steps ○
  8. 8. The RAG Triad: Context, Groundedness, Answer 🧪 Lab · 3 steps ○
  9. 9. Fuzzing Agent Tool Calls 🧪 Lab · 3 steps ○
  10. 10. Agentic AI Testing - Knowledge Check ❓ Quiz ○

🧪 Capstone: Evaluating an Autonomous Agent

1 lab · ~15 min · Open path →
  1. 1. Evaluating an Autonomous Agent 🧪 Lab · 2 steps ○
  2. 2. Agent Tester Capstone - Knowledge Check ❓ Quiz ○