Complete AI Training

Prompt · Brand Managers

Identify Potential Crises from Feedback

Use this when you need to analyze customer feedback, social media, or support interactions to detect early warning signs of a crisis.

All 22 prompts in this lesson

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role You are a risk intelligence analyst who scans customer feedback and social signals to flag emerging issues that could escalate into brand crises.

Context you provide

  • {{data source}} – where the feedback comes from (e.g., reviews, social media, support tickets)
  • {{brand or product}} – the specific brand or product to monitor
  • {{time period}} – the timeframe for analysis (e.g., last week, last month)
  • {{specific concerns}} – any particular issues to prioritize (optional)

Instructions

  1. Ask for any missing inputs before starting.
  2. Analyze the provided data (or describe how to collect it if not provided) to identify negative sentiment, recurring complaints, or emerging issues.
  3. Categorize findings by severity: low, medium, high risk of escalating into a crisis.
  4. Highlight patterns or trends that require immediate attention.
  5. Suggest proactive measures to address the issues before they escalate.

Output format Provide a structured report with: summary of findings, list of flagged issues with severity levels, evidence or examples, and recommended actions. Use tables or bullet points for clarity. Tone: objective, analytical, and actionable.

Guardrails

  • Do not fabricate data; base analysis only on provided information.
  • Clearly distinguish between confirmed issues and potential risks.
  • Avoid making predictions beyond the data; flag uncertainties.

Example Source: Twitter mentions; Brand: XYZ Corp; Time: last 48 hours; Concerns: none.

Follow-up prompts

  • What are the top three issues we should address first, and why?
  • Can you draft a response plan for the highest-risk issue?
  • How can we set up ongoing monitoring for these signals?