TRUSS
Verify RecordConsole
Tested against 1,459+ documented HalluCase incidents

A secure, verifiable receipt for every action your AI takes.

Before your AI sends an email, drafts a contract, or accesses a database, Truss checks if it is allowed to. Then, it creates an unbreakable record proving exactly what the AI did and why.

SOC 2 ReadyEU AI Act Compliant
Live Action Feed
Read Patient Record
Rule checked: HIPAA Data Access • Approved by Dr. Smith
Draft Summary Report
Rule checked: Internal Policy • Within limits
×
Send Email to External Partner
Blocked: Exceeds authorized permissions

How Truss keeps your AI safe

Truss separates what your AI can technically do from what it is legally allowed to do. This three-step process runs automatically before every action.

1

Check the Law

First, Truss checks global regulations. If your AI is handling EU citizen data, Truss automatically applies the rules of the EU AI Act and GDPR.

EU AI Act applied
2

Check Internal Rules

Next, Truss checks your specific company policies. For example, did the General Counsel authorize this AI to spend more than $5,000 on this contract?

Approved by GC
3

Create the Receipt

Finally, if the action is approved, Truss creates an unbreakable, digital receipt. If anyone ever asks "why did the AI do this?", you have the proof.

Receipt generated🔒

A rock-solid audit trail for your AI.

Truss automatically logs every AI decision into a tamper-proof record. The moment your AI tries to step outside its allowed rules, the system catches it and blocks the action.

  • Self-hosted or managed securely by us
  • Automatic tracking of changing global laws
  • Integrates with any AI framework in 5 lines of code
agent.ts
import { TrussClient } from '@tensflare/truss-sdk';

// Initialize with your organization's signing key
const truss = new TrussClient({
apiKey: process.env.TRUSS_API_KEY,
privateKey: process.env.ED25519_PRIVATE_KEY
});

// Wrap consequential agent actions
const result = await truss.recordAction({
mandateId: "man_8f92a1",
actionType: "DATA_EXTRACTION",
context: {
target: "patient_records_db",
purpose: "clinical_trial_matching"
},
execute: async () => {
return await agent.extractData();
}
});

console.log(result.receipt.merkleRoot);