Send a One-Page Proposal Minutes After Every Sales Call

In your AI notes app, make a folder for sales-call notes. Every call you want a proposal for goes in this folder, so the automation only ever sees the right meetings.

Then build a one-page proposal template in Google Docs. Add your logo and standard wording, and use placeholders in double curly braces for the fields that change per client. A good set of fields is:

• {{client_name}} and {{client_email}}
• {{current_problem}} and {{desired_outcome}}
• {{scope}} (three items)
• {{deliverables}}
• {{timeline}}
• {{investment}}
• {{assumptions}}
• {{next_step}}

Keep detailed legal terms in your existing standard agreement so the proposal stays on one page.

Open a new Zap and describe the whole workflow to Zapier's Copilot instead of adding steps one at a time. Use this prompt:

After a sales call, pull my notes here, have AI extract the info, fill my proposal template, and draft a prospect email.

Copilot will propose a chain that looks like this: Granola "Note Shared to Zapier" as the trigger, Claude "Send Message" to extract the proposal fields, Google Docs "Create Document From Template" to fill your template, Google Drive "Export File" to turn it into a PDF, and Gmail to draft the email.

Connect each app when Copilot asks, and pick the notes folder from Step 1 as the trigger source.

Open the Claude step and replace the default message with instructions that only use facts from the call. Ask for fixed fields rather than a free-form document so the Google Docs template receives predictable values.

Turn this sales-call note into the fixed proposal fields below. Use only facts from the note. Keep the proposal under 450 words. If the client email, price, scope, or delivery date is missing, write NEEDS CONFIRMATION for that field. Do not infer or invent commercial terms.

Fields: client_name, client_email, current_problem, desired_outcome, scope, deliverables, timeline, investment, assumptions, next_step, email_subject, email_body

Then map each field into the matching placeholder in the Google Docs step. The Drive step exports the finished doc as a PDF, and the Gmail step attaches it and uses the email subject and body from the AI.

Ask Copilot to set the last step to create a draft in Gmail, not send directly to the prospect. This keeps a wrong address or an invented price from ever reaching a client.

Optionally add a Filter step before Gmail that stops the Zap when any field contains NEEDS CONFIRMATION. Once you have several clean runs, you can switch the Gmail step to send automatically and keep the filter in place.

Run a test call with a fictional client and share the note to Zapier. Open the Gmail draft, read the email, and open the attached PDF.

Check three things before sending: the recipient address, the scope, and the price. Read the whole proposal, not just the numbers. In our tests, one run left the AI's own editorial about the budget sitting in the proposal instead of a clean number.

Pro tip: Add a Google Sheets logging step right after the AI extraction for a simple audit trail. Log the run time with details like the prospect name, company, key needs, and investment so you can see every proposal the Zap produced.