
Sauna finds the fits, reads the long RFPs, drafts the narrative from your past proposals, and tracks every deadline — so more of your week goes to the writing that wins.
Sauna is an AI assistant for grant writers that takes the legwork around the narrative. It finds and qualifies funding fits, reads long RFPs into clean checklists of every requirement, drafts from your proven boilerplate, and tracks every deadline and post-award report — so more of your week goes to the writing that wins.
What it does
Research funders and open calls against your organization's mission and eligibility, and summarize each fit with the amount, deadline, and odds.
Summarize a funding announcement into the eligibility, the required sections, the evaluation criteria, and a checklist of every attachment due.
Pull the right language from your past successful proposals and draft the narrative sections tailored to this funder's priorities.
Hold every submission deadline and post-award report due date in one view, with the reminder drafted before each one.
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.
“Read this 40-page NIH funding announcement, list every required section and attachment with its page limit, flag the evaluation criteria, and pull our matching boilerplate for the specific aims.”
Plugs into the tools you already run — and thousands more, or any MCP server.
What you get
Reports, drafts, and dashboards Sauna assembles from your live tools — kept current on its own.
Get the result, not the busywork.
Get started for freeGood to know
No. Sauna reads the RFP, drafts the narrative, and tracks the dates; submitting and the final say stay yours.
Yes. Connect your proposal archive and it pulls your proven language and tailors it to each funder's priorities.
Sauna reads only what you connect, and acts only after you approve. Your workspace and its memory are yours, not training data.
Keep exploring