Trust · detail

Security in detail.

Updated September 24, 2026

The detail behind the Trust page, for security, risk and architecture reviewers.

← Back to the Trust overview

Identity, access and isolation

Where your data goes

Ceez runs inside the environment you deploy it to. This is what is kept, where, and what can leave.

WhatWhere it livesLeaves your environment?
Source records: ERP, CRM, documentsYour systems, under the permissions they already enforceNo. They are read in place, not bulk-copied.
Derived knowledge: definitions, lineage, the knowledge graph, rulingsCeez Ground, in your deploymentNo
Agent memory and sample valuesCeez Ground and Crew, in your deploymentNo
Audit recordsYour deployment, hash-chainedNo
Model prompts and outputsThe model endpoint you configure: your provider under your keys, or a self-hosted modelOnly to that endpoint. With a self-hosted model and no outside calls, nothing leaves.
Provider keysYour infrastructureNo

What agents can and cannot do

The audit trail

Every query, decision and API action is recorded and hash-chained to the one before it, so a change to an earlier entry is detectable and any run can be replayed. It is tamper-evident: it shows that a record was altered rather than preventing the alteration. The trail stays in your deployment, so an auditor can inspect it without asking us.

This is what a short run leaves behind. Each entry carries a hash of the one before it, so changing an earlier entry breaks every later hash.

TimeWhoWhatEntry hashPrevious
09:02:11Crew · finance closeRead the sub-ledger, read-only7c1e…a9040000…0000
09:02:40Crew · finance closeMatched three differences to their sourcesa904…5be27c1e…a904
09:03:05Crew · finance closeProposed a journal, over the single-approver limit5be2…d310a904…5be2
09:14:52ControllerApproved, 1 of 2d310…88f75be2…d310
09:20:07Finance directorApproved, 2 of 288f7…2c6ad310…88f7
09:20:08Crew · finance closePosted the journal2c6a…e1b388f7…2c6a

Illustrative example · not customer data

Security reviews

We expect to be evaluated. During a walkthrough, our engineers walk your security and architecture teams through deployment, identity and access, data flows and the audit trail, and we respond to security questionnaires as part of your evaluation. Contact info@ceez.ai to start one.

Responsible disclosure

If you believe you have found a security vulnerability in Ceez or ceez.ai, please tell us. We appreciate reports from the security community and will work with you to resolve them.

How to report

Email info@ceez.ai with the subject line “Security report”. Please include:

What you can expect from us

Good-faith research

We will not pursue legal action against research carried out in good faith under this policy. Please avoid privacy violations, data destruction and service disruption; only interact with accounts you own or have permission to test; do not access, modify or keep data that isn’t yours; and give us reasonable time to fix an issue before disclosing it publicly.

Out of scope: denial-of-service testing, social engineering or phishing of our staff, physical attacks, and automated scanner output without a demonstrated impact.

Architects: the technical overview and feature catalog. Machine-readable contact details are published at /.well-known/security.txt.

Get started

Give Ceez one objective.

See how Ceez turns a real business objective into a working, governed AI workforce. A Ceez engineer uses the FDE Workbench to understand your environment, ground the objective and show you how it would run, with controls from day one.

  • A 45-minute walkthrough with an engineer
  • Your objective, scoped against your own systems
  • Your environment: your cloud, your data center, or air-gapped
  • Your controls, from day one

Prefer email? Write to info@ceez.ai

Ask for a walkthrough