Write an OKR set that is not wishful with a prompt built for ChatGPT and Claude. It supplies context, constraints and an output contract, then asks the model to surface assumptions and gaps. Copy it, fill the variables and treat the result as a structured draft, not a final answer.
4.8(33 ratings)663 copies
Updated By Author
51 words · v1.0
Fill in the blanks · 2 variables
ChatGPT promptReplace every highlighted token before sending
Write OKRs for {team} next quarter. Give one objective and three key results with baselines, targets and measurement method. Distinguish leading from lagging indicators. Add the three initiatives most likely to move each result and the one we should probably drop. Flag any result that is not actually measurable.
Context:
{context}
---
Platform note: Work through the task step by step, then give the final answer in the requested format. Ask one clarifying question if a required detail is missing.
Share what worked, what broke and which model you used. Comments appear after posting and are moderated for spam.
How to use this prompt
1
Open ChatGPT and start a new chat. Paste the prompt exactly as written.
2
Replace each placeholder ({team}, {context}) with your own details. Leave the instructions and the output format untouched.
3
Add one concrete example or data point if the model's first answer is vague. Specific input produces specific output.
4
Run it once, then ask for a single revision with a specific critique rather than regenerating from scratch.
5
Review the result. Every number, market claim and legal or financial implication with the accountable owner.
Worked example
This is the kind of input the prompt expects and the shape of output it produces. Your result will differ with the model and the details you supply.
Example input
Team: your team
Context: Add the relevant business or project context.
Example output
**Recommendation:** focus the next quarter on retention before adding a second acquisition channel.
**Why:** churn is 4.1% monthly, CAC payback is 11 months and the top two customers are 38% of revenue. The acquisition plan assumes a sales hire who is not yet hired.
**Trade-offs:** slower top-line growth for two quarters; the board should expect a flat new-logo number.
**Next steps:** interview 10 churned customers, ship the onboarding fix, set a 30-day review. **Assumption:** the churn data excludes involuntary churn; verify that before circulating.
Tips for a better result
Supply the actual numbers and constraints. The model cannot diagnose a business it cannot see.
Ask for the strongest argument against the recommendation; it exposes weak reasoning fast.
Require assumptions to be labelled separately from evidence.
Change one variable at a time and compare the outputs; it is the fastest way to learn what this model responds to.
Common mistakes
Sending a model-generated strategy memo to a board without checking the numbers.
Letting the model invent market sizes or competitor facts.
Asking for a recommendation before defining the decision and the constraints.
Verified Knowledge · FAQ
Questions about this prompt
Practical answers about running the write an okr set that is not wishful prompt.
Related prompts
Same job, a different angle — or the next step in the workflow.
A business prompt for turn a process into a runbook. It gives ChatGPT and Claude a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.
Build a hiring scorecard with a prompt built for ChatGPT and Claude. It supplies context, constraints and an output contract, then asks the model to surface assumptions and gaps. Copy it, fill the variables and treat the result as a structured draft, not a final answer.
Write a sales discovery call plan with a prompt built for Claude and ChatGPT. It supplies context, constraints and an output contract, then asks the model to surface assumptions and gaps. Copy it, fill the variables and treat the result as a structured draft, not a final answer.
ClaudeChatGPT
4.9(46)808 copies
A
Written and reviewed by Author
AIPrompt123 Contributor
Contributing author and prompt engineer at AIPrompt123.
Last reviewed 21 December 2025 · version 1.0 · tested on ChatGPT, Claude
Comments
Share what worked, what broke and which model you used. Comments appear after posting and are moderated for spam.