Learn AI
Build your understanding from AI fundamentals to production AI systems.
Prefer a guided sequence? Explore Learning PathsProduction AI / LLMOps
Operate AI systems reliably once they’re live — evaluation, observability, cost, and deployment.
8 conceptsLLMOps Fundamentals
LLMOps applies DevOps-style discipline — versioning, testing, monitoring — to prompts, models, and the pipelines around them.
Intermediate · 4 minPrompt Evaluation
Evaluating a prompt means testing it against a fixed set of cases before and after any change, not just eyeballing a few outputs.
Intermediate · 4 minModel Evaluation in Production
Production model evaluation tracks quality continuously against real traffic, not just a one-time benchmark before launch.
Advanced · 4 minLLM Observability Tools
Tools like Langfuse, LangSmith, and Arize Phoenix trace every model and tool call so a developer can see exactly what happened.
Intermediate · 4 minCost Monitoring for AI
Monitoring AI cost means attributing token spend to specific features, users, or tenants, not just watching one total bill.
Intermediate · 4 minReliability & Fallbacks for AI Systems
Reliable AI systems define a fallback model or provider, retry policy, and timeout before a provider outage ever happens.
Advanced · 4 minPrompt & Model Versioning
Versioning prompts and pinning model versions makes behavior changes traceable instead of silent.
Intermediate · 4 minCI/CD for GenAI
CI/CD for GenAI runs prompt and evaluation suites automatically before a prompt or model change ships to production.
Advanced · 4 min