Risk scoring
Each action is scored on amount, data sensitivity, and the agent's past behaviour, in milliseconds.
TrustCore
TrustCore sits between your AI agents and the systems they touch. Each action is checked against your rules and scored for risk, then allowed, blocked, or sent to a person, with a record kept every time.
How a decision is made
Pick a request to watch it pass through each check. The same four questions are asked whether the action is a database read or a payment.
refunds-agent refund.create(amount=1,850 USD)Which agent is this, and who is it acting for?
Verified: refunds-agent for support team
Is this action allowed by your rules?
Rule: refunds above 500 USD need approval
How risky is it, given amount, data, and history?
Risk 0.64: above threshold
Allow it, block it, or ask a person?
Sent to a supervisor in Slack
What it stops
What happens: A customer email tells the agent to ignore its rules and export data.
What TrustCore does: The export is checked against policy, not the prompt, so it is blocked.
What happens: An agent loops and issues the same refund forty times.
What TrustCore does: Rate and amount limits stop it and alert the owner after the first breach.
What happens: An agent tries to include personal data in a reply to a third party.
What TrustCore does: Sensitive fields are detected and the message is blocked or redacted.
What happens: An agent starts calling tools it was never meant to use.
What TrustCore does: Only approved tools are callable. Anything else is denied and logged.
What happens: A model update changes how the agent behaves.
What TrustCore does: Decision patterns are monitored and Veridict gates every new version.
Capabilities
Each action is scored on amount, data sensitivity, and the agent's past behaviour, in milliseconds.
Write rules in plain, versioned files. Review them like software and roll them back if needed.
Risky but legitimate actions wait for a named approver in Slack, email, or the console.
See every agent, every action, and every decision as it happens, with alerts on unusual patterns.
A signed, append-only record of every decision, ready for auditors and the Evidence Center.
We attack your agents with injection, jailbreak, and misuse tests before attackers do.
Getting started
Every deployment starts in observe mode: decisions are recorded but nothing is blocked. Once the rules match how you work, switch to enforce.
Wrap your agent's tools in a few lines of code. Works with any framework.
Best for teams building their own agents
Route agent traffic through a TrustCore gateway. No code changes.
Best for vendor and third-party agents
Run TrustCore inside your own environment, next to your agents and data.
Best for regulated and air-gapped teams
Pair it with PrivateStudio for private models, Veridict for release testing, and the Evidence Center for audit evidence.
TrustCore in depthQuestions
TrustCore checks the action itself, outside the model. Each tool call is verified against identity, policy, and risk before it runs, so a manipulated prompt still cannot reach a system the agent is not allowed to use.
Yes. It works with any agent framework, model, or vendor agent through an SDK, a gateway with no code changes, or a self-hosted deployment.
Yes. Actions above a limit or outside normal patterns are routed to a named approver in Slack, email, or the console before they run.
Every deployment starts in observe mode, which records what TrustCore would decide without blocking anything. You switch to enforcement when the rules match how you work.
Connect one agent in observe mode. You will see every action it takes and what TrustCore would have decided, before anything is blocked.
Request a demo