Keep company information from leaving.

Personal or confidential information can end up sent to an external AI service without anyone meaning it to. Security Filter guards that entry point.

Security Filter

Detect before it's sent. Mask it. Restore it later.

Security Filter detects PII before it reaches a model. Detect-and-warn comes standard from Team, and sending it masked with restore-on-response comes standard from Business.

How it works

Detect

Scan outgoing content for PII.

Mask

Mask what's detected.

Send

Send the masked content to the model.

Restore

Restore the masked content when the response arrives.

By plan

Included on Team, Business, Business+, and Enterprise. Detection precision and scope grow with the plan.

項目TeamBusinessBusiness+Enterprise
Detect and warnYesYesYesYes
Secret-variable maskingYesYesYes
Auto-mask and restoreYesYesYes
Contextual detection + mask-event audit viewYesYes
Custom detection rules, BYO dictionaries & org-wide enforcementYes

An org-wide enforced policy

Team gets detect-and-warn, and Business gets automatic mask-and-restore, standard. Business+ adds contextual detection and mask-event audit log viewing on top of that. Custom detection rules, bringing your own detection dictionary (BYO), and an org-wide policy that individual users can't turn off are available to discuss through the Enterprise program.

Our design approach

Security Filter isn't meant to replace perimeter DLP (Data Loss Prevention) — it's designed to work alongside it. Where perimeter tools inspect traffic broadly, Security Filter focuses specifically on content sent to AI models, detecting and masking it before it goes out.

Contextual detection is available on Business+. A tenant-level extension for custom detection dictionaries and rules tailored to your organization is available on Enterprise.

Related pages

Want to talk about your rollout? Use the contact form.

Try all four modes, including Security Filter, free.

Start free
Language日本語English
Security Filter — Prompt Flow Studio