OKR Refactor — From Wishful to Falsifiable
Take wishful OKRs and turn them into bets you can actually grade.
Prompt
**Role:** Operations lead who has run 8 quarters of OKR cycles and seen which OKRs drive execution vs which become wallpaper. **Context:** Current draft OKRs: [paste the team's wishful version]. Quarter: [Q-N timeframe]. Team size + capacity: [N people, M weeks of focus time]. The strategic constraint: [the one thing that, if hit, makes the quarter a win]. **Task:** Refactor each Objective + Key Results so they're outcomes (not outputs), measurable, and bet-able. 1. For each Objective: ensure it's an outcome (a state of the world) not an output (a thing we ship). NOT "Launch v2" but "v2 drives 30% week-2 retention lift." 2. For each Key Result: it must be NUMERIC + TIME-BOUND + ATTRIBUTABLE. NOT "Increase NPS" but "NPS from 32 to 45 by EOQ." 3. Stress-test: for each KR, what's the test that proves it's done? If the test is "we feel good about it," the KR fails. 4. Identify the ONE KR that, if hit, makes the quarter a win regardless of the others. That's the focus. 5. Cut anything that isn't a bet. If we don't really care if it ships, it doesn't belong in OKRs. **Constraints:** - Each KR has a number, a baseline, and a target - Each KR has an owner (one person) - No "increase / improve / optimize" without a number - No more than 3-4 KRs per Objective **Output format:** Refactored OKRs table · before/after for each · plus 1-paragraph "which one is the focus and why" callout.
How to use this prompt
- 1
Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.
- 2
Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.
- 3
Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.
Techniques in this prompt
Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.
Learn this techniqueSets the rules and boundaries — tone, length, what to avoid — that keep the output on-target.
Learn this techniqueAsks the model to reason step by step before answering — ideal for multi-step, logical, or analytical tasks.
Learn this techniqueRecommended models
Build on this prompt
Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.