In Adventure 03: The AI Observatory, you are a rogue SecUnit aboard the Perihelion (ART). You need to jump to RaviHyral, but ART is “multitasking” and refusing to calculate the coordinates.
Your mission? Diagnose the distraction, quantify the obsession, and fix the navigation system.
Intermediate: The Distracted Pilot
In this level, you will dive deeper into RAG (Retrieval-Augmented Generation) observability and custom metrics.
What You’ll Learn:
- RAG Instrumentation: How to trace a full RAG pipeline (LangChain + Qdrant) with OpenLLMetry.
- Custom Metrics: How to implement OpenTelemetry Counters in Python to track specific business logic.
- PromQL & Recording Rules: How to write Prometheus queries to calculate a “Distraction Ratio”.
- Debugging RAG: How to use traces and metrics to find and fix retrieval issues.
The Tech Stack:
- Python & Ollama (Local LLM)
- LangChain & Qdrant (Vector Database)
- OpenTelemetry & OpenLLMetry
- Jaeger & Prometheus
- Kubernetes (pre-provisioned)
New Verification System: Verify your solution instantly inside your Codespace and get your Certificate of Completion!
Ready to Start?
Good luck, SecUnit. ART is waiting (and watching Sanctuary Moon). 
Credits: The characters of this adventure are borrowed from the fantastic Murderbot Diaries series by Martha Wells! 
Reduce Telemetry Noise: Adventure 03 | Expert is Live!