How it works

How AgentTrustCore keeps agents in check

Follow one agent from a private model to an audit report, then see exactly how TrustCore decides what an agent is allowed to do.

How it works

From your data to proof, five products in one flow

Each product does one job and hands its result to the next. Follow one agent, a claims intake agent for an insurer, as it moves from private model to audit report. Select any stage to see what goes in and what comes out.

Step 1 of 5 · PrivateStudio

Train a private model

We train a small language model on your own documents and terminology, and run it in your cloud or data centre. Your data is never sent to a public AI provider.

Goes inYour documents, records, and past decisions
Comes outA domain model that runs inside your environment
See the PrivateStudio page
PrivateStudio outputExample
model
claims-slm-v3
hosted in
your-vpc / eu-west
trained on
internal claims archive
data sent out
none

It is a loop: blocked actions and audit findings become new Veridict tests for the next release.

What is TrustCore

Think of it as access control and an audit trail, built for software that makes its own decisions.

Companies already control what employees can do: accounts, permissions, approvals, and logs. AI agents need the same controls, applied automatically and at machine speed. TrustCore, the core of the AgentTrustCore platform, provides exactly that.

01

It sits in the request path

Agents never call your systems directly. Each tool call passes through TrustCore first, so nothing executes without a decision.

02

Permissions come from identity

Every agent has its own identity and scope, like an employee account. What a prompt says cannot widen what the agent is allowed to do.

03

Every decision becomes evidence

Allowed, blocked, or escalated, each outcome is written to a signed, append-only record your auditors and customers can rely on.

Observability

A complete trace of every agent run

Each tool call, policy check, and decision is timed and stored. Your team can search, filter, and replay any run to understand exactly what an agent did and why.

Run traceExample data
1,247
Requests
23
Blocked
12ms
Avg Latency
8
Active Agents
TimeAgentActionDetails
14:32:01
research-agentweb_searchquery: "market trends 2026"
14:32:01
research-agentpolicy_checkdata-access-policy
14:32:02
research-agentALLOWEDlatency: 8ms
14:32:15
finance-agenttransfer_fundsamount: $50,000
14:32:15
finance-agentrisk_analysisscore: 0.82
14:32:16
finance-agentBLOCKEDexceeds limit
Showing last 9 events→ View full dashboard