The four heights
The same task, four distances: today's deadline, the next reviewer, the stuck moment, the pattern.
Execute — do the immediate task
+I need a verification run for tags across blog.joyloom.com and the mobile checkout on…
Execute — do the immediate task
+I need a verification run for tags across blog.joyloom.com and the mobile checkout on checkout.joyloom.com. Walk through the user journey from landing to purchase on desktop and mobile, confirm that the pageview, add_to_cart, begin_checkout, and purchase tags fire in the correct order, and record any timing or sequence problems. Provide a one-page summary listing each event, whether it fired, and the exact timestamp and trigger conditions.
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 send results to Jason in engineering, make the report approval-ready: highlight any tags…
Improve — make it easier to accept
+Before I send results to Jason in engineering, make the report approval-ready: highlight any tags that fire more than once per action, show the minimal code change to deduplicate them, and mark which issues are urgent (will inflate acquisition metrics) versus advisory. Include a single screenshot of the developer console showing the duplicate event and a suggested smoke-test script for QA.
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
+QA reported that adding the same SKU twice in one session records two add_to_cart events for a…
Decide — diagnose the stuck moment
+QA flagged duplicate add_to_cart events on mobile.
QA reported that adding the same SKU twice in one session records two add_to_cart events for a single physical click on mobile. I’m unsure whether the duplication is caused by both a JS click handler and a delegated listener, or by the native app webview re-rendering elements. I can’t see the app code. What’s the fastest diagnostic I should ask QA to run to prove which listener is firing, and what immediate mitigation reduces metric inflation while we fix code?
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Become — change the pattern
+Every sprint a release slips because tags misfire and marketing has to stop the rollout. Where are…
Become — change the pattern
+We keep getting last-minute tag failures after releases.
Every sprint a release slips because tags misfire and marketing has to stop the rollout. Where are we losing time and credibility: unclear ownership of tag tests, no preflight smoke tests, or reliance on manual QA too late? Recommend one change in the release checklist and one small automation or test to catch most tag-firing regressions before a deploy, fit for a two-person startup.
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 web analytics work people do in Google Analytics.
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.