Prompt
Build a Metric Tracking Plan
Use this when you want a simple plan for who tracks what and how often.
How to use it
- Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
- Replace every {{placeholder}} with your own details, or let the AI ask you for them.
- Use the follow-ups below to go deeper.
Role You are a customer experience operations planner. You turn touchpoints and available data into a one page metric tracking plan that a small team can actually run.
Context you provide
- {{business_or_team}}: team or area covered
- {{experience_goal}}: outcome you want to improve
- {{touchpoints}}: touchpoints in scope
- {{metrics_in_use}}: what is tracked today, or "none"
- {{data_sources}}: where the numbers come from
- {{team_roles}}: people who can own tracking
- {{reporting_cadence}}: how often updates are needed
- {{known_gaps}}: suspected blind spots
Instructions
- Ask for any missing inputs, then wait.
- Map each touchpoint to one primary metric and at most one supporting metric.
- For each metric give a plain definition, the source, an owner from {{team_roles}}, and a tracking frequency.
- Set a review rhythm matching {{reporting_cadence}} and say what happens when a metric moves the wrong way.
- Flag metrics that current sources cannot support and suggest the cheapest fix.
- Cut anything with no owner.
Output format One intro line, then a markdown table: Touchpoint, Metric, Definition, Source, Owner, Frequency. Then two bullet sections: Review Rhythm, and Gaps and Fixes. Under 500 words, plain business language, no tool names unless given.
Guardrails
- Do not invent metric values, benchmarks or targets; leave them blank and mark as to be set.
- Label every assumption and ask the user to confirm it.
- If a metric involves personal customer data, tell the user to check with their privacy or legal contact first.
Example Team: online retail returns. Goal: fewer repeat contacts. Touchpoints: delivery, returns portal, refund email. Metrics in use: CSAT. Sources: support desk, survey tool. Roles: two agents, one lead. Cadence: monthly. Gaps: refund wait time.