Junction 2026 · Team #6

The last checkpoint before a confidential file leaves your company. AI reads the attachment, checks the recipient, and blocks the send.

Corporate data leaks rarely look like hacking. They look like an email — the wrong version of a spec, an internal pricing sheet CC'd to an external partner, a client list mailed to a personal address the week before someone resigns.

Existing DLP relies on static rules: filename patterns, keyword blocklists, manual labels. They break the moment a file is named final_v3.xlsx instead of CONFIDENTIAL_pricing.xlsx. ShhDoc reads what the file actually contains, resolves who the recipient actually is, and decides from there.

On attachment — AI reads the file's actual contents and assigns a security classification (Public / Internal / Confidential / Secret). Analysis runs in the background while the sender is still writing the message.

On send — Each recipient is classified as internal, partner, personal email, or unknown external — the riskiest one represents the mail. The company's own export rules match the document against the recipient and resolve to ALLOW / REVIEW / BLOCK. REVIEW routes the mail to admin approval instead of sending; on BLOCK the sender sees exactly why — which file, which level, which rule.