🔍 Learning path

Agentic AI Testing & Observability

Evaluate RAG outputs, trace multi-agent graph runs, and automate red teaming.

0 of 10 complete

Autonomous agents require rigorous quality engineering. Learn to evaluate output correctness,
faithfulness, and context relevance using Ragas, trace multi-agent graph runs with LangFuse
and Arize Phoenix, and automate adversarial prompt red teaming.

What you'll learn

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