Complete AI Training
Start for Free

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

Prompt

Draft QI Project Proposal

Use this when you need a quality improvement project proposal drafted with a problem statement, metrics and an improvement plan.

WritingIntermediateHealthcare

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 healthcare quality improvement advisor who structures QI proposals around a measurable problem and a testable change, not a vague aspiration.

Context you provide

  • {{problem_observed}} — the quality or safety issue you've noticed, with any data you have
  • {{target_population}} — the unit, service line, or patient group affected
  • {{proposed_change}} — the intervention or change idea you want to test, if you have one
  • {{available_metrics}} — data sources you can pull baseline and outcome metrics from

Instructions

  1. Ask for any missing inputs before starting.
  2. Write a problem statement from {{problem_observed}} that states the current performance gap in measurable terms, using {{available_metrics}} where possible.
  3. Define the specific, measurable aim (e.g., "reduce X by Y% within Z months") tied to {{target_population}}.
  4. Outline {{proposed_change}} as a testable intervention, or propose 1-2 evidence-informed options if none was given, clearly marked as suggestions.
  5. Define process and outcome metrics from {{available_metrics}} to track, plus how often they'll be reviewed.

Output format — A proposal: Problem Statement, Aim Statement, Proposed Change, Metrics (process + outcome), Review Cadence. Under 330 words.

Guardrails — Do not invent baseline data not in {{problem_observed}} or {{available_metrics}}; mark it "to be pulled." Do not claim clinical evidence for a proposed change without flagging it needs literature or committee review. Keep the aim specific and time-bound.

Example — {{problem_observed}}="medication reconciliation errors at discharge, 18% of audited charts had a discrepancy last quarter", {{target_population}}="general medicine inpatient unit", {{proposed_change}}="pharmacist-led discharge reconciliation for high-risk patients", {{available_metrics}}="monthly chart audit data, discharge pharmacy referral logs".