Check customer damage photos on return claims and flag pictures that were reused or copied from the web: AI agent prompt
When a customer says an item arrived broken, most shops ask for a photo, then someone has to look at every picture, judge the damage and decide on a refund or replacement. An AI assistant can describe what each photo actually shows, check it against the product and the claim, and flag photos that look reused, stock-like or identical to another claim, so staff only spend time on the doubtful cases. At Salesforce's Dreamforce, Australian online retailer Kogan said (reported by iTnews on Oct 14, 2026) that its Agentforce customer service agent uses generative AI image recognition to assess transit damage in return cases, and that it now catches people who submit the same image across cases or a damaged-product picture found online.
Customer SupportReturn damage checksbeginnerThe prompt
Help me review damage photos for return and refund claims. For each claim I will give you: claim ID, product name and model, what the customer says is wrong, order date and delivery date, and the photo(s). [paste or upload claims and photos]. For every claim: 1) Describe exactly what the photo shows (item, angle, visible damage, packaging, background). 2) Say whether the photo matches the product and the complaint (yes / partly / no) and why. 3) Rate the damage: cosmetic, functional, or can't tell. 4) Flag warning signs: the same or a near-identical photo used in another claim in this batch, a picture that looks like a stock or catalog image, wrong model or color, no packaging when the customer says it arrived damaged, or damage that looks like wear and tear. 5) Suggest a next step: approve, ask for one more specific photo (say which), or send to a person to review. Give me a table I can paste into a spreadsheet, plus a short list of claims that need a human. Never reject a claim yourself and never accuse a customer; just mark it for review. Our return policy: [paste policy].
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 ChatGPT, Claude, Gemini and review the answer before you use it.
Works with: ChatGPT, Claude, Gemini, Zendesk/Intercom AI, Salesforce Agentforce, Google Sheets
Real-world example: itnews.com.au/news/kogan-taps-ai-agent-to-handle-customer-service-6296
Featured in: Free AI agent prompts for small business (beginner-friendly) · AI prompts for Google Sheets and Excel work · ChatGPT prompts for customer service: ticket triage, replies and handoffs
Before you use it: what to check
Already built into this prompt
- Give me a table I can paste into a spreadsheet, plus a short list of claims that need a human.
- Never reject a claim yourself and never accuse a customer; just mark it for review.
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 →