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 subscribers tagged by their behavior before the Monday newsletter goes out. Tag anyone who…
Execute — do the immediate task
+I need subscribers tagged by their behavior before the Monday newsletter goes out. Tag anyone who opened at least two of the last five emails as Engaged-2+, anyone who clicked any link in the last 30 days as Clicked-30, and anyone who visited our pricing page in the last 14 days as Pricing-Visited. Apply tags without changing their existing segmentation, and export a brief report listing how many new tags were added and a sample of 20 email addresses for each tag.
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 we finalize these behavior tags, surface decisions that will make approval fast: show counts…
Improve — make it easier to accept
+Before we finalize these behavior tags, surface decisions that will make approval fast: show counts for each prospective tag, prioritize tags by predictiveness of purchase (opens vs clicks), highlight overlaps (people getting both Engaged-2+ and Clicked-30), and flag any tags that would change who is in our VIP flow. Put the recommended top three tags to keep and the two I should drop to avoid over-segmentation.
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 filtered for people who opened two of the last five emails and the count is much higher than…
Decide — diagnose the stuck moment
+I ran the engagement filter and got unexpected numbers.
I filtered for people who opened two of the last five emails and the count is much higher than expected. I fear my open metric is inflated by image loads or auto-openers and will over-tag inactive users. What is the likely cause, how dangerous is it to use open-based tags for the VIP flow, and what safer alternative or tweak should I apply right now?
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Become — change the pattern
+Over months our tag list has become noisy: many behavioral tags get created before a campaign and…
Become — change the pattern
+We repeatedly create tags that no one uses later.
Over months our tag list has become noisy: many behavioral tags get created before a campaign and then never relied on. Which tagging habits are costing us time and accuracy, and what three changes will reduce tag sprawl: a governance rule for creating tags, a retirement schedule for unused tags, and a naming convention to show purpose and last-used date?
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 email marketing work people do in Mailchimp.
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.