Spot a brewing brand crisis early by having an agent watch social posts, reviews and support messages for unusual spikes: AI agent prompt
A bad product batch, a viral complaint or a rude staff video can spread for hours before anyone on the team notices, and by then the story is set. AI agents can scan social mentions, reviews and support messages, spot an unusual jump in a complaint or negative tone, show who is spreading it, and draft a response plan. On Oct 22, 2026 Sprinklr announced its Voice of the Customer agent suite in Google's Gemini Enterprise Agent Marketplace, including a Crisis Monitoring agent that detects emerging issues, assesses how far they are spreading, identifies key amplifiers and supports response planning, alongside agents for brand health and competitor benchmarking.
MarketingBrand crisis early warningintermediateThe prompt
Here are our brand mentions from the last 72 hours: [paste social posts, reviews and support messages with date, platform and follower count if known]. Here is what a normal week looks like for us: [typical number of mentions per day and usual complaints]. 1) Compare the last 72 hours to normal and tell me if any topic, complaint or product is spiking. Show the numbers. 2) For anything spiking, summarize what people are saying in plain words with 3 real quotes, when it started, and the 5 accounts with the most reach that are spreading it. 3) Rate the risk as low, medium or high and explain why. 4) Draft a holding statement, a reply template for customers who ask, and a short note for our team about what to do and not say. 5) Tell me what to watch over the next 24 hours. Only use the posts I gave you; don't guess at anything not shown.
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, Perplexity, Google Alerts, Buffer
Real-world example: investors.sprinklr.com/news/press-releases/detail/265/sprinklr-announc
Before you use it: what to check
Already built into this prompt
- Only use the posts I gave you; don't guess at anything not shown.
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