Our CRM is a mess before we start.

The plan

Create a consistent intake review queue. 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

Create a staging sheet with intake_id, company, contact_name, service_requested, source_quote, missing_fields, duplicate_check, status. Keep email addresses in your approved CRM. Copy a small anonymized set of enquiry text and define which fields your CRM requires.

Use this fictional sample for your first run:

INTAKE I01: I am Jo from Example Retail. We need help auditing inventory in two shops. Please send information.
REQUIRED: company, contact_name, service_requested.
EXISTING COMPANY: Example Retail. Existing record ID: CRM-42.

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.

Extract only explicit company, contact_name and service_requested values. Include an exact source_quote supporting each field. Return missing_fields for absent requirements. Do not infer an email, budget, phone number or buying intent. Return a proposed record only, not a command to create or update a CRM entry.

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

I01 → Example Retail | Jo | inventory audit for two shops. Duplicate check points the reviewer to CRM-42; no new company should be created until identity is resolved.

4. Put the checked result to work

Compare the proposed record with the source. Search the CRM using the actual approved contact details and company domain. If a match exists, review whether to update it; otherwise approve a new record. Enter it manually, record its CRM ID in staging, and mark that intake ID processed.

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

Run the same intake twice, then one without a company and one mentioning two businesses. Do not create duplicate or ambiguous records. If you later automate, reuse intake IDs and keep the approval gate described in the linked n8n guide.

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.