Our leads go cold.

The plan

Draft the next useful message for every waiting lead. This is a manual, AI-assisted workflow: you copy approved inputs into Claude, check the output, and move the accepted result into your existing process. Start with the synthetic example below.

You need access to Claude and your team’s approved document or spreadsheet workspace. Use only data your business permits in those services. Tool plans and limits vary; this walkthrough does not require an API connection.

1. Prepare a small, useful input

In Google Sheets create lead_id, last_contact, request, approved_offer, next_action, draft, owner, status. Select five leads you already have permission to contact. Use a stable lead ID and remove personal details from the copy you send to Claude.

Use this fictional sample for your first run:

LEAD L01: Asked whether we offer an inventory audit. Last reply: requested a sample scope.
APPROVED OFFER: A 30-minute discovery call, followed by a scoped proposal. No price or delivery date has been agreed.
OWNER: Sam.

2. Give Claude a precise job

Open a new chat at claude.ai. Paste the prompt below, then paste the sample after it under a heading called INPUT. For a PDF, attach the sample file to the chat instead. Keep the source and instructions clearly separated.

For each lead, write one follow-up under 90 words using only the request and approved offer. Include one question that moves the request forward. Do not claim a past relationship, invent availability, add urgency, offer discounts, or make a delivery promise. Return lead_id, draft, missing_information and next_action. Missing context means clarification, not guessing.

INPUT:
[Paste the sample or your approved source here.]

Read the response before continuing. If required columns are missing, ask: “Return the same result using every requested column. Mark unsupported fields UNKNOWN.” Do not fill gaps by asking the model to guess.

3. Check against the expected result

L01 → a brief message offering to discuss the inventory audit and asking which inventory locations the scope should cover. No invented price, appointment time, or deadline.

4. Put the checked result to work

Check the lead against your CRM and confirm no colleague has already replied. The named owner edits and sends through the existing email thread. Record the sent date and agreed next action in the CRM; keep sensitive contact information out of the model output.

Keep a status of draft, needs clarification, approved, or completed beside each item. A draft is not a completed action. If the service is unavailable, use the original source and your normal manual process.

5. Test the awkward cases

Test a lead with no request, one already answered, and one asking for an unapproved discount. The first needs clarification, the second stays out of the sending queue, and the third makes no discount promise. Track time to first human reply.

Run the same cases again after changing the prompt or source. Keep the input, output, correction, and reviewer decision together. Expand only when someone can reliably check the results.

If the result is off

Narrow the input to one record and recheck the source. For missing facts, ask the process owner. For an unsupported statement, remove it and add an explicit constraint to the prompt. If the same failure repeats, do the task manually until the source or instructions are fixed.

Scope: This is an original illustrative recipe with synthetic data, adapted from the field guides below. It is not a live-tested integration or a claim of time saved. Claude’s file-upload documentation explains supported attachments; the copy-and-paste path does not need file uploads.