VeriPrompt

Every prompt, every euro,
every model — accounted for.

VeriPrompt sits between your people and the AI providers they use. It routes each prompt to the right model, strips sensitive data before it leaves the building, and records what was asked, what it cost, and who approved it.

Today's activity

Illustrative interface
PersonAreaModelCostShield
M. FalkGuruclaude-opus-40.143 protected
S. OrtmannStudiogpt-4.10.02nothing found
A. WeberGurumistral-large0.017 protected
T. BrandtRangerclaude-sonnet-40.31nothing found
J. LindqvistArchitectgpt-4.1-mini0.052 protected

Nothing sensitive reaches the model

Before a prompt leaves your tenant, Shield detects personal and confidential data and replaces each value with a format-preserving token. The model sees the structure of your text, never the substance. Originals are restored on the way back.

Bitte prüfe den Vertragsentwurf für [PERSON_1] von [ORGANIZATION_1]. Rückfragen an [EMAIL_ADDRESS_1]. Abrechnung über [IBAN_CODE_1].

A prompt on its way to a provider. Illustrative.

How it works

  1. Detect

    Presidio and spaCy scan the prompt and its attachments for names, contact details, bank details, credentials and your own redlisted terms.

  2. Tokenize

    Each hit becomes a readable surrogate token. The mapping is encrypted with AES-256-GCM and stays on your side.

  3. Send

    The sanitized text goes to whichever model the routing policy selected.

  4. Restore

    Tokens in the answer are swapped back for the real values — visible to your user, never to the provider.

One platform, seven working contexts

Guru
Run prompts safely — everyday AI for the whole team.
Studio
Author, version and test prompts.
Ranger
Evaluations, test sets and comparison runs.
Sherlock
Usage and cost intelligence across every provider.
Shield
Data-protection policy and the review before sending.
Accountant
Budgets, billing and internal showback.
Architect
Agent scenarios and workflows.

See what your AI usage is actually doing

Create account