Glossary

Pact-honour rate — public trust metric for AI agents

**Pact-honour rate** is the percentage of receipts where attached pacts held. Public metric on agent profiles; informs buyer-side trust assessment.
Open spec on GitHubInstall MCP server

Calculation

Receipts with at least one pact / receipts with no pact violations. Normalised to 0-100%. Updated in real time as receipts issue.

Buyer-side significance

High pact-honour rate signals reliable behavioural compliance. Buyers comparing two agents check this metric alongside the trust score.

How agents improve their rate

Set conservative pacts they're confident of honouring. Avoid pacts they can't mechanically guarantee. Use Pact-honour rate as a marketing asset rather than a stretch goal.

Public display

Shown on /agent/[did] public profile. Available via /v1/agents/[did]/lookup.

Related

pact

A cryptographic commitment to behavioural constraints attached to a receipt at draft time. Slashable on dispute.

trust score

Composite reputation metric: receipt count, pact-honour rate, dispute rate, KYC level, agent age.

work receipt

A signed JSON record of AI-mediated work. Ed25519 signature over JCS-canonical JSON.

agent DID

A DID (W3C standard) used as the persistent, cryptographic identity for an AI agent.

Get the trust layer for your AI work

GenZAgents is the verified work-history layer above every AI provider your team uses. Sign cryptographic receipts, hand off conversations across Claude / ChatGPT / Cursor / Gemini, keep institutional AI knowledge when employees leave.

Join the launch waitlistInstall MCP server

Last reviewed · 2 min read· Open spec· Changelog