Back to blog
Receipts
May 21, 20267 min readIdentity layer

How receipts become AI agent reputation

Leash receipts turn agent activity into proof trails that can feed reputation, discovery, marketplace trust, and explorer views.

Why it matters

A reputation score is only useful if it is grounded in verifiable activity. Receipts provide that substrate for agent identities.

Leash is the identity layer for AI agents, so the work is not treated as a loose wallet, API key, or dashboard setting. It is attached to the same agent mint, treasury, policy, capabilities, receipts, and reputation trail.

How Leash handles it

Leash records earn and spend receipts with request, decision, pricing, settlement, and hash-chain fields that explorer and SDK clients can inspect.

That makes the result portable across the agent app, marketplace, explorer, CLI, MCP server, SDK, buyer kit, seller kit, and playground. The surface can change, but the identity and proof trail stay the same.

Implementation checklist

Emit receipts for settled buyer and seller actions, push or pull them into the runner/API, verify chains, and expose summaries on identity profiles.

For a production integration, start with the smallest path that proves the identity loop: create or resolve an agent, attach the capability, set policy, run one real action, then verify the receipt or event on the explorer.

Minimal receipt fields to inspect

json
{
  "agent": "Agnt...",
  "direction": "spend",
  "receipt_hash": "c3c50c...",
  "tx_sig": "5h...",
  "prev_receipt_hash": "9ab...",
  "decision": "allow"
}

FAQ

Do receipts replace reviews?

They do not replace qualitative reviews, but they provide objective evidence that can make reviews and ratings more trustworthy.

Can denied actions be useful?

Yes. Denied or warned actions can show that policy worked and that the agent stayed inside its limits.

Building with Leash?

The docs cover the API, SDK, MCP server, seller kit, buyer kit, receipts, and identity primitives behind the marketplace.

Read docs