The four heights
The same task, four distances: today's deadline, the next reviewer, the stuck moment, the pattern.
Execute — do the immediate task
+Apply the Product View and Repeat-7d Add+View segments to the Monthly Behavior report and the…
Execute — do the immediate task
+Apply the Product View and Repeat-7d Add+View segments to the Monthly Behavior report and the Checkout funnel, then export the two filtered reports and email them to Priya in marketing and Tom in product with a Thursday deadline.
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 filtered reports, make the segment application obvious: put segment name and size at…
Improve — make it easier to accept
+Before I send filtered reports, make the segment application obvious: put segment name and size at the top of each report, ensure the time range matches across reports, surface differences in conversion rate between segments, and flag any report where sample size falls under 200 sessions so reviewers don't overinterpret it.
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
+I applied our Repeat-7d Add+View and Product View segments to the Monthly Behavior and Checkout…
Decide — diagnose the stuck moment
+I filtered the conversion report and the percentages flipped strangely between segments.
I applied our Repeat-7d Add+View and Product View segments to the Monthly Behavior and Checkout reports and conversion rates shifted in a way that surprised Priya and Tom. I fear I've mismatched date ranges or included users vs sessions. I can't tell which setting caused the flip. What's the most likely misconfiguration and how do I verify it quickly?
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 losing credibility because reports show different numbers depending on who applied…
Become — change the pattern
+Each analyst applies segments differently and stakeholders get inconsistent numbers.
We keep losing credibility because reports show different numbers depending on who applied segments. I'm responsible for consistent reporting. Which single standard (date handling, user vs session scope, or naming) will reduce these inconsistencies most, and how do I operationalize it so everyone follows it?
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.