Let a support agent decide fair fee or penalty waivers from real signals—weather, attendance patterns, policy—so agents stop rubber-stamping every missed-class or no-show request: AI agent prompt
OpenAI's Nov 5, 2026 cult.fit customer story describes moving customer support from a mostly human-led chat model toward AI-first workflows inside Sprinklr. One example: when a member asks to waive a penalty for a missed group fitness class, an AI agent assesses the request using signals such as local weather and that class's attendance patterns before deciding whether the fee should be waived, with connections into cult.fit backend systems. Cult.fit reports more than 50% reduction in customer support costs alongside the broader AI rollout (Codex standardization, AI Trainer, and support agents). The waiver flow is presented as a concrete agent decision path grounded in policy and signals rather than free-form chat. Figures are cult.fit's as reported by OpenAI.
The prompt
Build a fee/penalty waiver agent for my support desk. Policy: [paste waiver rules], signals I can check: [weather API, attendance, tenure, prior waivers], systems: [support tool, billing]. Rules: never waive outside policy; never invent weather or attendance; escalate chargebacks, repeated abuse, and VIP exceptions. 1) Turn my policy into a decision tree with clear yes/no/escalate branches. 2) List required signal checks in order. 3) Draft customer-facing grant and deny replies. 4) Propose audit log fields and a weekly false-grant review. 5) Give a two-week pilot plan with success metrics (auto-resolve rate, reopen rate, $ waived). Do not change a real account in this chat.
Fill in the blanks, then copy
This prompt has 3 [bracket]s to fill in. Type your details below and the prompt updates as you go. Your answers stay in this browser and are reused on other prompts with the same blanks. Nothing is sent to us.
Example values are fictional, just to show how a filled-in prompt reads. Replace them with your real details.How to use it
- Copy the prompt above.
- Replace every [bracket] with your own details (use the fill-in-the-blanks box above, which remembers your answers for the next prompt).
- Paste it into ChatGPT, Claude, Sprinklr (or Zendesk/Intercom) and review the answer before you use it.
Works with: ChatGPT, Claude, Sprinklr (or Zendesk/Intercom), your billing system, weather/attendance APIs
Real-world example: openai.com/index/cultfit-builds-with-codex/
Featured in: Free AI agent prompts for small business (beginner-friendly) · AI prompts for writing SOPs, reports, policies and checklists
Before you use it: what to check
Already built into this prompt
- Rules: never waive outside policy; never invent weather or attendance; escalate chargebacks, repeated abuse, and VIP exceptions.
- Do not change a real account in this chat.
Check yourself
- 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".
- Check names, dates, numbers and any claim against your own source material before you use the answer. AI can misread or invent details.
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 freeMore Customer Support prompts
See all Customer Support prompts →