
Sauna pulls historical sell-through from your warehouse and Shopify, builds the baseline forecast by SKU, layers in promo and seasonality, and drafts the consensus deck for the S&OP meeting.
What it does
Sauna pulls two years of unit history from Snowflake and Shopify and writes a baseline statistical forecast per SKU into your Google Sheet, with the method and error noted.
It reads the promo calendar from Airtable and adjusts the forecast for known lifts, drafting the promo-uplift assumptions for you to confirm.
Sauna compares last period's forecast to actuals, computes MAPE and bias by category, and drafts the accuracy summary highlighting the worst-fit SKUs.
It assembles the demand-review deck in Google Slides — baseline, overrides, and risks — for the monthly S&OP sign-off.
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.
“Pull 24 months of unit sales from Snowflake, build a baseline forecast for my top 50 SKUs, and flag where last month's bias was over 15%.”
Plugs into the tools you already run — and thousands more, or any MCP server.
Good to know
No. For new or sparse SKUs it says so and falls back to an analog or a flat assumption you choose, rather than fabricating a curve.
No. It keeps your overrides separate from the baseline and shows both, so the consensus number is always traceable to who set it.
Sauna reads only what you connect, and acts only after you approve. Your workspace and its memory are yours, not training data.
Keep exploring