The four heights
The same task, four distances: today's deadline, the next reviewer, the stuck moment, the pattern.
Execute — do the immediate task
+Users report the date picker crashes in Safari 14. Reproduce the bug in Safari on macOS, localize…
Execute — do the immediate task
+Users report the date picker crashes in Safari 14. Reproduce the bug in Safari on macOS, localize the offending code in date-picker.js where Intl.DateTimeFormat is used, add a feature detection fallback for the Safari behavior, test in Chrome and Firefox, and push 'fix: date picker Safari fallback' by Thursday so marketing's demo works.
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Improve — make it easier to accept
+Before I change the date picker to handle Safari, make the fix easy to approve: show the Safari…
Improve — make it easier to accept
+Before I change the date picker to handle Safari, make the fix easy to approve: show the Safari stack trace and the Intl call suspected, propose a minimal feature-detection fallback with a short comment explaining why it's needed, and list the browsers/versions tested so the reviewer can focus on the compatibility risk rather than re-reading the code.
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Decide — diagnose the stuck moment
+The date picker works in Chrome but throws in Safari 14. I suspect Intl.DateTimeFormat differences…
Decide — diagnose the stuck moment
+The date picker fails only in Safari and I don't know why.
The date picker works in Chrome but throws in Safari 14. I suspect Intl.DateTimeFormat differences but I'm unsure which behavior to rely on. I am the release owner for the demo and can't delay. Which quick diagnostic confirms whether Intl is the issue, and what is the safest fallback to implement instantly that won't break Firefox or Edge?
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Become — change the pattern
+We keep shipping features that work in Chrome but fail in other browsers, causing late QA…
Become — change the pattern
+Cross-browser bugs keep appearing late in QA.
We keep shipping features that work in Chrome but fail in other browsers, causing late QA fire-drills. Root causes seem to be missing cross-browser testing, implicit reliance on modern APIs, and no feature-detection patterns. Which single process change will reduce these late failures the most: adding a Safari VM to CI, requiring feature detection for all new APIs, or a compatibility checklist during PR? Which is fastest to adopt for our small team?
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Next to this one
Other programming language work people do in JavaScript.
Every task here came from the work, not from a feature list — which is why the prompts name what you want done and never the button that does it. The tool changes; the work does not.
Copyright © LLOS.ai · 2026 — original pedagogy, voice, and design — all rights reserved.
The rest of the map
Same library, five ways in.