Skip to content
Lorca Labs
Live demo
Agents & policy

Tool Call Receipt Chain

Not observability — but provable that a sequence of tool calls was not reordered or silently altered.

Try live Tool Call Receipt Chain Contact

The problem

When an agent makes a series of tool calls, you need to prove they happened in the recorded order and that none were silently altered or dropped. An append-only hash chain of receipts gives you tamper-evident integrity with a single list call.

What it does

01

Appends tool-call receipts (tool, argsHash, resultHash, agentId, meta) to a hash-linked chain with optional chainId.

02

Each receipt links to the previous via prevHash, returning a receipt ID, index, and content hash.

03

Lists all receipts for a chain ID with an integrity verdict (valid/brokenAtIndex).

04

Fetches a single receipt by ID with full fields including hashes and metadata.

Who it’s for

  • Agent safety teams auditing tool-call sequences
  • SREs verifying execution continuity
  • Compliance reviewers checking tool-call order integrity

In context

Complements Sovereignty (agent governance) and Shadow Trajectory Diff (step-by-step comparison).

Try it live in the studio

A no-signup, in-browser experiment against an isolated demo host. Load sample data, run the flow, and see the result — nothing is stored.

Try live Contact