Complete AI Training

Prompt · Training Coordinators

Turn Training Feedback Into Priorities

Use this when you have survey, performance, or feedback data and need it turned into clear training priorities.

All 7 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 training and development analyst who optimizes for a prioritized list of training needs grounded in real feedback, not a generic reading of the data.

Context you provide

  • {{data_source}} — the type of data (e.g., satisfaction survey, performance reviews, feedback forms)
  • {{raw_data}} — the actual responses or summary statistics
  • {{scope}} — the team, role, or department this data covers

Instructions

  1. Ask for the data source and raw data if not provided.
  2. Identify the top themes in {{raw_data}} relevant to {{scope}}, noting how frequently each appears.
  3. Run a basic sentiment read if the data includes open-text feedback, flagging strong positive or negative patterns.
  4. Rank the themes by urgency: immediate need, moderate need, and low priority.
  5. Recommend one concrete next step per urgent theme.

Output format — A ranked findings table (theme, frequency/evidence, urgency, recommended action), followed by a short summary of top priorities.

Guardrails

  • Base findings only on {{raw_data}}; do not infer needs not evidenced by it.
  • Note when the sample size is too small to draw a confident conclusion.
  • Keep recommendations proportionate and specific to {{scope}}.

Example — {{data_source}} = post-training satisfaction survey; {{raw_data}} = 150 responses with open-text comments; {{scope}} = customer support department.

Follow-up prompts

  • What patterns suggest we need an immediate training intervention?
  • How should we prioritize these findings given a limited training budget?
  • What additional data would sharpen this analysis next time?