The seat census that asked first
A founder-owned hospitality and travel marketing agency of 40 to 59 people paid for AI seats for everyone, but the owner couldn't say what staff used them for, and a past AI roadmap never ran.
Owner can't say what staff use AI seats for
With each person's opt-in, it reads exported AI chats, redacts guest data, and groups work into task types, with rare ones folded away so no one is singled out. The owner gets a 1-page, anonymous answer. The top task, resort package copy, becomes one shared skill with style checks.
- 4 declined exports excluded before parsing, 0 of them opened, and 0 staff ids found in the 20 files the run wrote
- the shared skill turned 1 rate sheet into 4 channel listings and passed 30 of 31 checks; 1 flagged, the social post held for a person on the banned word 'nestled'
- Chat export analysis
- Opt-in consent gate
- PII redaction
- Keyword rules clustering
- Shared skill with style checks
- Automated self-check
Same problem?Send it over.
Tell me what your version looks like and which tools it runs in. I reply with how I would build it.
-
Customer experience consulting
The handoff that broke in front of the client
the runner wrote 29 work-in-progress files and 8 reached the client's folder, every one traced by the audit to a sealed approval; the 2 injected failures added 0
-
Marketing agency
The clip desk that reads its own drop-off
the desk pinned 6 of 6 drops to a transcript line and an export row; against the drops we designed into the curves ourselves, it found 6 of 6 and 0 of 1 decoy dips fired
-
Creator marketing agency
The library that hands each creator back their own best openings
all 42 concept lines across 4 briefs cite the same creator's own posts: 98 citations, 0 to another creator, by construction and checked by the run