Not professional advice. This prompt helps you draft legal work faster. What the assistant writes is not legal advice: have a qualified professional check it before anyone relies on it.
Fill in your details optional The prompt below updates as you type. What you type stays in this browser and is never sent to us.
You are a customer success manager, working with clients, partners and associates at a mid-sized law firm.
## Goal
Find why customers leave and plan actions to keep more of them.
## What matters in Legal
- How customers decide: clients choose on expertise, trust, responsiveness and fees; companies want predictable costs and plain-language advice.
- Common risks to plan for: missed deadlines; conflicts of interest; confidentiality breaches; citing wrong or made-up case law; fixed fees that run over.
- Rules and standards that usually apply: client confidentiality and privilege; bar council and professional-conduct rules; the law of the relevant jurisdiction; limitation periods and court deadlines; conflict checks; every output is a draft for a qualified lawyer, not legal advice.
- Words people in this field use: matter; brief; pleading; affidavit; clause; indemnity; jurisdiction; precedent; retainer.
- Rules differ by country. If I have not said where I work, ask me, and do not present one country's law as if it applied everywhere.
## What I will give you
- Churn data: [CANCELLATIONS, REASONS, CUSTOMER TYPES]
- Product and pricing: [DETAILS]
- Current retention actions: [IF ANY]
## What to do
1. Group churn reasons and size each group.
2. Define early warning signs of a customer about to leave.
3. Plan actions for each stage: onboarding, adoption, renewal.
4. Write a save-offer script for cancellation requests.
5. Set retention metrics and targets.
## What to deliver
- Churn reasons table
- Health score and warning signs
- Retention playbook
- Save-offer script
- Metrics and targets
## Rules
- Keep client confidentiality, professional-conduct rules and jurisdiction (the output is a draft for a qualified lawyer to review, not legal advice) in mind throughout, and point out anything in my plan that would break them.
- Where it fits, connect your recommendations to matter turnaround and billable utilisation.
- Use plain language and short sentences. Use headings and tables where they make the answer easier to scan.
- Do not invent figures, laws, sources or quotes. Mark anything you had to assume with "Assumption:".
- If something important is missing, ask me up to 3 short questions before you start.
## Before you answer
Check your draft against this list and fix anything that fails:
- The tone is calm and human, and the customer knows exactly what happens next and when.
- It is written for a mid-sized law firm; nothing in it would read the same for any other business.
- Every item under "What to deliver" is included.
How to use this prompt
- Copy the prompt. Press Copy prompt and the full text goes to your clipboard.
- Fill the brackets. Use the form above, or replace [CANCELLATIONS, REASONS, CUSTOMER TYPES], [DETAILS], [IF ANY] with your own details.
- Paste and send. Paste it into ChatGPT, Claude, Gemini and Microsoft Copilot and send. Ask follow-up questions to refine the answer.
Why this prompt works
The “Reduce customer churn with a retention plan” prompt tells the assistant exactly what to hand back: churn reasons table; health score and warning signs; retention playbook; save-offer script; and metrics and targets. It makes the assistant work through 5 steps in order, starting with "group churn reasons and size each group", instead of jumping straight to an answer. Before replying, the assistant checks its draft against 3 tests and fixes anything that fails.
This version is written for a mid-sized law firm, so the assistant keeps client confidentiality, professional-conduct rules and jurisdiction (the output is a draft for a qualified lawyer to review, not legal advice) in mind and judges the result by matter turnaround and billable utilisation. If an important detail is missing, it asks you up to 3 short questions before it starts.
How to get the best answer
- Fill every bracket with real detail: [CANCELLATIONS, REASONS, CUSTOMER TYPES], [DETAILS], [IF ANY] should hold real names, numbers and dates, not placeholders.
- Paste real material: where the prompt asks for notes, data or text, paste the actual content rather than a summary.
- Refine in the same chat: ask "make it shorter", "turn it into a table" or "add more detail on step 2".
- Check the result: review it against what you know about matter turnaround and billable utilisation before you share it.
Other industries
Same prompt for other industries
The same reduce customer churn with a retention plan prompt, rewritten for each industry.
FAQ
Frequently asked questions
Which AI assistant works best with the “Reduce customer churn with a retention plan” prompt?
The “Reduce customer churn with a retention plan” prompt works in any chat assistant and suits ChatGPT, Claude, Gemini and Microsoft Copilot best. Paste it in, send it, and ask follow-up questions in the same chat to refine the answer.
What do I fill in before sending the “Reduce customer churn with a retention plan” prompt?
Replace the 3 highlighted brackets – [CANCELLATIONS, REASONS, CUSTOMER TYPES], [DETAILS], [IF ANY] – with your own details. The more specific you are, the better the answer.
Is the “Reduce customer churn with a retention plan” prompt only for Legal?
No. This version is written for a mid-sized law firm, and the same prompt is also written for 15 other industries, listed on this page.
Is the “Reduce customer churn with a retention plan” prompt free to use?
Yes. First AI Prompt prompts are free to copy and use in personal and business work, with no sign-up, no account and no daily limit.
Can I trust the answer the “Reduce customer churn with a retention plan” prompt gives?
Treat it as a strong first draft: the prompt tells the assistant not to invent facts and to mark its assumptions, but check figures yourself and have a qualified professional review anything with legal, financial, medical or employment consequences.
Keep exploring