Tenant boundaries
Tenant-scoped authorization and storage boundaries are designed to prevent one customer from accessing another customer’s data.
Security and trust
Short answers first. Each points to the setting, the document or the record that backs it. Where we can’t show evidence yet, we say so.
01 · Assurance
Each badge opens the evidence. We show nothing we can’t link.
Select a mark to see what it is and where the evidence is.
AARM · runtime implementer in the technical working group
AIUC-1 · mapping our decision records, in progress. No conformance claim.
02 · Your data
You choose, per workspace, whether tool arguments are stored, hashed, redacted or dropped. A change applies to data that arrives after it.
| Data | Default | Kept for |
|---|---|---|
| Tool arguments | Hashed, with a key per workspace | With the decision record |
| Prompts, model output, tool results | Dropped | Not kept |
| Decision records | Stored | 90 days |
| What an approver sees on a held action | Masked, at most 500 characters | Deleted when the action is resolved |
| Ask Thoth conversations | Visible only to the person who started them | 90 days after the last message |
| A trial workspace | The same defaults | 30 days, then 30 days read-only, then deleted |
Workspace settings
Data handling
Tool arguments
Argument names are kept. Each value is kept as a hash, not readable.
Prompts, model output and tool results
Nothing is kept.
Tenant-scoped authorization and storage boundaries are designed to prevent one customer from accessing another customer’s data.
Confirmed for the deployment you select and your agreement, not assumed.
03 · Access
Administrative and service access is scoped by role, and an integration only gets the permissions for its stated purpose.
04 · When something fails
Failure behavior belongs in policy. A sensitive workflow can stop or ask for approval, while a lower-risk one can use a fallback you define.
05 · Evidence
Each decision keeps integrity data with its record, so later changes can be detected within the evidence system you configure.
Build a signed evidence pack for a period of up to 31 days and verify it offline with thothctl evidence verify: no network, no account, no call to Aten. Receipts and packs are signed with separate keys, and the fingerprints are published.
What verify checks
Today you build and verify with thothctl, the API, Terraform or MCP. The dashboard can’t download or verify a pack yet.
See the signing keys06 · Where it runs
Compute in Azure West US 2. Queues, keys and storage in AWS us-west-2. Customers are separated by workspace.
Tell us your requirement and we will say what is possible.
Thoth is hosted only today. We will say so plainly until this is available.
07 · Subprocessors
| Provider | What it does for Thoth |
|---|---|
| Microsoft Azure | Hosting, databases and backups |
| Amazon Web Services | Email delivery, key management, secrets, evidence and report storage |
| WorkOS | Sign-in |
| Azure OpenAI | Powers Ask Thoth |
| Stripe | Billing on paid plans |
| Slack | Approvals and notifications, when you connect it |
08 · Evaluate it
The path a security team takes before a pilot, in four steps.
Select a step to follow the path.
By industry
Assurance, subprocessors, hosting location and retention are on this page, each with its source.
Signed evidence packs your auditor verifies offline. Stream decisions to your SIEM to keep them as long as your policy requires.
Every change is previewed, then confirmed by an admin with a recent second factor.
The integration passes the fields you configure for evaluation: identity, task, session, tool, resource and environment. Customer tools and resources stay outside Thoth’s control plane.
Step 1 of 4
Your code runs the agent and holds its credentials. Before a tool runs, your integration asks Thoth what to do and waits for the answer.
Source identities, tool credentials and resource permissions stay with you.
Select a step to see what it does and what crosses it.
Only US-origin models: OpenAI models on Azure OpenAI, or OpenAI’s open-weight models on an OpenAI-compatible endpoint.
It does not replace your approval process. It holds the action and shows a person what it would do, and a person decides. It does not claim to make an agent safe: it checks each action against your policies before it runs, and keeps the record.
SOC 2 Type I and ISO/IEC 42001, with the evidence in the Trust Center. SOC 2 Type II, GDPR and the CISA Secure by Design pledge are in progress, and we show no badge for any of them until it is complete. AIUC-1 is a mapping in progress, not a conformance claim.
Email security@atensecurity.com. The disclosure page lists scope and safe-testing guidance. We ask you to coordinate before publishing.
Backed by
Advised by security leaders from
In standards work with
Mapping our decision records to
Bring your questionnaire. We’ll walk through boundaries, data handling, failure behavior and the assurance material available for your evaluation.
For technology, channel, federal delivery, and research partnerships.
Help improve Thoth. Allow Amplitude and Mixpanel to measure page use, interactions and errors across the Aten Security website, documentation, signup and dashboard. We exclude customer content and credentials. Your choice does not affect access. You can change it in Analytics preferences.