Tutorials

Tutorials

Complete, runnable walkthroughs

• Reusable Capabilities — Compose Summarizer, Translator, and SentimentClassifier onto an editorial role with zero method bodies.
• REST API actions with @WebService — Bind any REST endpoint to an LLM-callable action through annotations alone. GET + query, path templating, POST + body + custom headers, retry.
• Declarative Guardrails — Validate, sanitise, and bound action parameters and return values through @InputGuardrail / @OutputGuardrail annotations, no per-action plumbing.
• Declarative RAG with @KnowledgeSource and @Retrieval — Wire knowledge sources to a Role and retrieve from them on every action call through annotations alone, no manual vector-store plumbing.
• Declarative Resilience — Wrap action dispatch with structured tracing, latency + counter metrics, and automatic recovery via @Traced / @Metered / @Fallback.
• Research Agent — Agent that searches the web, reads PDFs, and produces cited summaries.

Architecture sketches + building blocks

Each of these pages describes the shape of a non-trivial system and links to the framework pieces you'd compose to build it. The full code walkthrough is still being written — start the implementation today and open a discussion if anything's missing.

• Customer Support Bot — RAG over a knowledge base, with sentiment-aware escalation handoff.
• Multi-Agent Research Team — Coordinator + specialists + judge.
• Agent with Tool Approval — Destructive tools gated through a human approval UI.