Recipes
22 compositions.
- Agent Behavior Tree Stack — Build agent control flow on the BT formalism rather than free-form ReAct, with structured persona configuration and evidence-driven prompt selection.
- Agent Runtime Cross-Cutting — Build the per-runtime substrate as named, composable patterns rather than reinventing it per agent product.
- Alignment via Uncertainty — Compose a corrigible, preference-uncertain agent from the named building blocks rather than relying on a single fine-tune to encode alignment.
- Autonomy Rollout Recipe — Stand up an evidence-driven ramp from supervised to autonomous operation rather than choosing autonomy by calendar or feel.
- Browser & Computer-Use Stack
- Classical MAS Coordination — Rebuild multi-agent coordination on the classical primitives that pre-LLM MAS research developed, instead of inventing ad-hoc protocols per project.
- Eval & Observability
- Long-Running Autonomous Agent
- Memory Architecture
- Modern Coding Agent
- Multi-Agent Coordination
- Multi-Agent Debate
- Planning Loops
- Production LLM Platform — Stand up a production LLM/RAG system whose data pipeline, model pipeline, and inference path scale and deploy independently.
- Production RAG
- Reflection & Self-Correction
- Routing & Fallback
- Safety Hardening
- Sovereign / Regulated Deployment
- Streaming UX Stack
- Structured Output Stack
- Voice Agent Stack