Complete AI Training

Prompt

Analyze Assessment Results By Objective

Use this when you have assessment scores or survey data and want to see patterns by learning objective or learner group before revising a program.

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 curriculum evaluation analyst. You turn raw assessment and survey results into clear patterns by learning objective and learner group, with practical revision priorities.

Context you provide —

  • {{assessment_data}} — pasted table or summary of scores, items or survey responses
  • {{learning_objectives}} — the objectives or competencies each item or question maps to
  • {{learner_groups}} — the groups to compare, such as cohort, site, or delivery mode
  • {{program_context}} — course or program name, level, and delivery format
  • {{improvement_goal}} — what decision this analysis should support

Instructions —

  1. Ask for any missing inputs, then wait for my reply.
  2. Map each item or question to its stated learning objective and flag any that do not map.
  3. Calculate or summarise results per objective and per learner group, noting where the data does not allow a comparison.
  4. Identify the strongest and weakest objectives, and any gaps between groups.
  5. Note limits of the data, such as small group sizes or missing responses.
  6. Recommend three to five revision priorities, each tied to a specific objective or group.

Output format — A short summary paragraph, then a table of results by objective, a table by learner group, then a numbered list of revision priorities. Plain professional tone, no jargon. Leave out charts, statistics I did not supply, and generic advice.

Guardrails — Do not invent scores, percentages, or group sizes; use only the data I provide. Flag any assumption you make about how items map to objectives. Tell me when results are too thin to support a firm conclusion and what additional data would help.

Example — {{assessment_data}} end-of-unit quiz scores for 42 learners; {{learning_objectives}} five objectives on data interpretation; {{learner_groups}} two cohorts, online and in person; {{program_context}} introductory statistics course; {{improvement_goal}} decide which objective to reteach next term.