Build with agents
Patterns and primitives for building agent-native applications on NFH fabric.
Agents are first-class participants on NFH fabric. They hold identities, sign transactions, hold tokens, earn reputation, and are accountable for what they do.
Common patterns
Agent-owned account
Provision a DID for the agent. Issue it a capability credential. Fund a Tokenisation account in its name. The agent transacts under its own identity, with audit trails attached.
Delegated authority
Issue a time-bounded, scope-bounded credential from a human or organisation to an agent. The agent acts under that delegation; revocation is a one-call action.
Human-in-the-loop gating
Use Network Adapters Edge policy plug-ins to require human approval for actions above a threshold (value, risk, counterparty).
Multi-agent commerce
Discovery via MCP. Contracts via Network Adapters Edge. Settlement via Tokenisation. Audit via Observability & Audit. Agents brokering with agents, end to end.
Standards
MCP for discovery and service consumption. W3C Verifiable Credentials for capability and delegation. OpenTelemetry for action tracing.
What to read next
Last updated
Was this helpful?