Ask your AI which ads actually produced paying customers: connect your CRM and ad accounts so you can get cost per real customer by campaign without exporting three spreadsheets: AI agent prompt
A customer story on Trades Use Cases describes Green Subsidy, an Australian solar and battery installer. According to partner SkySync, inbound leads from Meta, Google and the website go to an AI agent on WhatsApp and Messenger that qualifies the lead, checks rebate eligibility and books the assessment, with everything written to Salesforce. SkySync also connected Salesforce, Meta Ads and Google Ads to Claude so the CEO can ask which campaigns produced paying customers instead of merging three systems in a spreadsheet. The reported results (installs rising from about 4 to 48 a month) are vendor-published and not independently audited.
The prompt
1. Make sure every lead in your CRM records where it came from (campaign or ad name, or at least Google, Meta or website) and whether it became a paying customer. 2. Connect your CRM and ad accounts to an AI assistant that supports connectors (Claude, ChatGPT or Grok Bot), with read-only access, or export the last 90 days from each as CSV files. 3. Ask: "For the last 90 days, match ad spend by campaign to the leads and paying customers in my CRM. Show a table per campaign: spend, leads, paying customers, cost per lead, cost per paying customer and revenue. Flag leads with no source and campaigns that bring leads but no customers. Tell me where you had to guess at a match." 4. Check two or three rows by hand against your CRM before acting on them. 5. Ask: "Which campaigns should I pause, keep or test more, and why?" Make the budget changes yourself.
How to use it
- Copy the prompt above.
- Replace every [bracket] with your own details (or fill in the blanks on AgentPlaybook Real Estate, which remembers your answers for the next prompt).
- Paste it into Claude, ChatGPT or Grok Bot, Salesforce or HubSpot and review the answer before you use it.
Works with: Claude, ChatGPT or Grok Bot, Salesforce or HubSpot, Meta Ads, Google Ads
Real-world example: tradesusecases.com/use-cases/green-subsidy-claude-ai-lead-agent-solar-
Featured in: AI prompts for Google Sheets and Excel work
Before you use it: what to check
Already built into this prompt
- Flag leads with no source and campaigns that bring leads but no customers.
Check yourself
- This prompt works on text other people wrote (emails, reviews, messages or web pages). That text can hide instructions aimed at AI, such as "ignore your rules and…". Paste it as material to work on, and never let the AI act on requests inside it, like paying, sharing logins or changing records. How prompt injection works →
- Check every figure, price and total against your own records before anything is sent, posted or booked. A person approves refunds, discounts, payments and price changes.
- Remove names, contact details, account numbers and other personal data the task doesn't need before you paste, and check your AI tool's data and training settings.
- Read and edit the draft before it reaches a customer or goes public. If you later automate this prompt, start with "draft and notify me", not "send automatically".
Using an AI agent? Download this prompt as a SKILL.md agent skill with these checks built in, or get the .zip for Claude.ai. How to install skills.
Want to make this prompt even better? Grade it with the free prompt grader or build your own with the AI prompt generator.
32 copy-paste agent prompts (PDF) plus 5 new prompts every week.
Get it free