# Stack layers

The agent-ready vertical stack: from contracts to evidence.

- [The discovery-to-governance control plane](control-plane.md) — The end-to-end lifecycle that turns a tool-calling model into governed agent execution.
- [Contracts and interfaces](contracts-and-interfaces.md) — Authoritative, machine-readable descriptions of what a capability is and how to call it.
- [Discovery and current-context retrieval](discovery-and-retrieval.md) — Finding that a capability exists, and selecting a small candidate set at inference time.
- [Understanding and grounding](understanding-and-grounding.md) — Schema grounding vs semantic grounding: matching types vs matching intent.
- [Identity and authorisation](identity-and-authorisation.md) — Establishing who or what is acting, for whom, for what purpose, with which limits.
- [Execution and orchestration](execution-and-orchestration.md) — Durable, stateful multi-step execution owned by the runtime, not the prompt.
- [Policy enforcement](policy-enforcement.md) — Decoupling policy decisions from enforcement points across the stack.
- [Observability and provenance](observability-and-provenance.md) — The evidence layer: traces, metrics, logs and an interoperable provenance graph.
- [The federation layer (the missing plane)](federation-layer.md) — The collaborative-learning plane that lets institutions improve a shared model without centralising data.