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 to save a single message I’ll need tomorrow afternoon. It’s the bug workaround Tom posted in…
Execute — do the immediate task
+I need to save a single message I’ll need tomorrow afternoon. It’s the bug workaround Tom posted in #backend at 4:12 p.m. — save that message so I can find it quickly and confirm the steps before the deploy on Friday.
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 save this message for later, make it obvious why I’ll care at 2 p.m. tomorrow: surface the…
Improve — make it easier to accept
+Before I save this message for later, make it obvious why I’ll care at 2 p.m. tomorrow: surface the author and timestamp, show the code snippet or link inline, and flag whether it’s already been acknowledged by QA so someone doesn’t follow an outdated workaround.
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
+Tom posted a workaround in #backend at 4:12 p.m. and I don’t have time to copy it. If I save it…
Decide — diagnose the stuck moment
+I just saw Tom’s workaround in #backend and I can’t trust I’ll find it later
Tom posted a workaround in #backend at 4:12 p.m. and I don’t have time to copy it. If I save it now, will I be able to retrieve the exact message and its context before Friday’s deploy? If not, what’s the fastest, reliable way to keep the message and its link tied to the deploy checklist so QA won’t miss it?
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 critical messages — workarounds, manager approvals, short-lived links — between when…
Become — change the pattern
+I repeatedly lose critical single messages before they’re needed
We keep losing critical messages — workarounds, manager approvals, short-lived links — between when they appear and when we need them. Help me change a habit that prevents that: what consistent saving or tagging routine should I adopt so engineers don’t scramble before deploys and managers stop asking “where was that?”? Include one simple rule I can enforce teamwide.
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 team chat work people do in Slack.
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.