What’s Next
This tutorial is actively expanding. Here’s what’s coming:Multi-Agent Systems & Coordination
Multiple agents working together — workflow orchestration, agent-to-agent communication, and the A2A protocol.- Workflow Orchestration: Sequential and parallel agent pipelines
- Agent Orchestration: Agents that delegate to other agents
- A2A Communication: Agent-to-Agent protocol for cross-system coordination
Fine-Tuning
When prompting and RAG aren’t enough — training models on your data for specialized behavior.- When to Fine-Tune vs RAG: Decision framework
- Data Preparation: Building training datasets from production logs
- LoRA & QLoRA: Efficient fine-tuning techniques
- Evaluation: Measuring fine-tuned model quality
Evaluation & Observability
Production-grade monitoring and testing for AI systems.- LLM Evaluation Frameworks: Systematic testing beyond vibes
- Observability: Tracing, cost tracking, latency monitoring
- A/B Testing: Comparing model versions in production
- Regression Detection: Catching quality drops before users do
Want to contribute or suggest a topic? Open an issue on GitHub.