Use AI to Fix Your OKRs, Not Write Them
Use AI to refine your OKRs by creating a custom 'coach' prompt based on expert advice. This avoids leaking company strategy to public LLMs and makes even secure, weaker enterprise models useful for strategic alignment.
Why it matters
Asking a public LLM to write your OKRs is a critical error. It outsources your core strategic thinking and risks leaking sensitive company plans and priorities to a third party. The correct, secure approach is to use AI as a refinement tool, not a content generator.
The method
Instead of asking an AI to create OKRs, you create a custom, detailed prompt that acts as an expert "OKR coach." This prompt should encapsulate your team's or an expert's definition of what constitutes a strong OKR. You can build this prompt by collaborating with AI on your criteria, pointing it at an expert's public advice, or summarizing notes from a book or workshop. This coach prompt becomes a reusable asset.
What to watch
Once created, you can use this coach prompt inside your company's firewall with a secure, private enterprise LLM. You feed it your draft OKRs and ask it to critique them based on the rules within your prompt. This technique allows you to leverage AI for high-value strategic work safely, even if your internal model is less powerful than public ones. It shifts the engineering effort from generating text to creating a robust system for critique.
Interview question
What is the recommended approach for leveraging AI in your OKR process, according to the provided card?
- a.Using a public LLM to generate initial OKR drafts, then having human experts review and edit them.
- b.Developing a custom "OKR coach" prompt for an internal LLM to critique and refine human-drafted OKRs.Correct
- c.Training a dedicated internal AI model on company strategy to automatically produce all team OKRs.
- d.Submitting existing OKRs to a public AI for analysis to identify trends and suggest improvements for future cycles.
Why? this is the answer
The card explicitly states that AI should be used as a refinement tool via a custom "OKR coach" prompt with an internal LLM to critique draft OKRs, not to generate them. Option A is incorrect because it involves using public LLMs and outsourcing initial drafting, which the card warns against due to security and strategic risks.
Just read this? Test yourself on what you have been reading.
Read the original → scrum.org
Put your scrolling time to good use
Learn one idea, try a quiz and save useful cards for revision. Tezvyn makes it easy to learn and stay current in your tech field, a few minutes at a time.
The iPhone app is on the way
We are building it. Until it lands, nothing here is held back from you: every interview card, your saved cards, streaks and the job board all work in Safari, plus hundreds of free practice quizzes of thirty questions each. Sign in and it all carries over to the app the day it arrives.
Want it as an icon? Tap Share at the bottom of Safari, then Add to Home Screen. It opens full screen and the cards you have read stay available offline.
We are hiring for this. Every open role lists the topics its interview covers, so you can prepare for the real thing rather than guessing.
See open roles