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 found a video that violates community rules by promoting self-harm and grooming minors. Flag the…
Execute — do the immediate task
+I found a video that violates community rules by promoting self-harm and grooming minors. Flag the video for removal, attach timestamps at 0:12 and 0:39 where the behavior occurs, include the username DiegoMartinez99, and request urgent review by Trust & Safety because minors are explicitly targeted and the caption asks for private messages.
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 report this clip to Trust & Safety, make the case easy to act on: pull the two…
Improve — make it easier to accept
+Before I report this clip to Trust & Safety, make the case easy to act on: pull the two incriminating timestamps to the top, quote the caption text that asks viewers to DM, summarize why it fits the self-harm/grooming policy in one sentence, and list any visible personal data (faces, location, school logo) so reviewers can verify quickly.
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 watched a 30-second video where the creator tells teenage viewers to DM for 'help' and shows an…
Decide — diagnose the stuck moment
+I just watched a loop that directs viewers to message the creator privately.
I watched a 30-second video where the creator tells teenage viewers to DM for 'help' and shows an under-18 in the background; I’m worried it’s grooming but not sure if it’s explicit enough. The people involved are me (content moderator), the creator DiegoMartinez99, and the alleged minor. What is the likely policy classification and the best next action to escalate with clear evidence?
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 the past month I’ve flagged several clips that say 'DM me for help' and I end up delaying…
Become — change the pattern
+I keep hesitating on borderline videos that mention ‘DM for help’.
Over the past month I’ve flagged several clips that say 'DM me for help' and I end up delaying reports because I’m unsure when it crosses grooming or allowed outreach. Where am I losing time and safety credibility, and what single habit would most reduce delays and increase accurate escalations?
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 short-video platform work people do in TikTok.
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.