
Sauna assembles the alert investigation, drafts the case narrative, pulls the transaction and KYC evidence, and writes the SAR recommendation so each alert is dispositioned with a clean, sourced trail for your review.
What it does
Sauna gathers the triggering transactions, customer profile, and prior alerts from Snowflake, drafts the case summary in Google Docs, and lays out the activity timeline for review.
It writes the suspicious-activity narrative — who, what, when, where, why — citing the exact transactions and amounts, and holds it for your decision to file or clear.
Sauna assembles the customer's KYC, beneficial-owner, and counterparty information from the file in Google Drive and flags missing or stale due-diligence items.
It logs each alert's status, escalation, and deadline in Jira and drafts the hand-off note to the BSA officer so nothing ages past the regulatory clock.
Put Sauna to work on this.
Get started for freeIn context
Sauna shows up where you already work — the web app, Slack, email, iMessage, and Superhuman. It reads what it needs, does the task, and comes back with the draft for your approval.
Try it
The literal prompt for this job. Open it in Sauna and it picks up from there.
“Build the case for alert 5521 — pull the triggering transactions and the customer's KYC, lay out the timeline, and draft a SAR narrative if the structuring pattern holds.”
Plugs into the tools you already run — and thousands more, or any MCP server.
Good to know
No. It builds the case and drafts the narrative or clearance rationale, but the disposition — file, escalate, or close — is yours. Nothing is filed without your approval.
No. Every transaction, amount, and date in the narrative comes from your systems with the source shown. It flags missing KYC rather than inventing it, so the trail stays examinable.
Sauna reads only what you connect, and acts only after you approve. Your workspace and its memory are yours, not training data.
Keep exploring