The brief that knows where to look first
A 140-person health and wellness communications agency moving over half its work to fixed fee, where finding the right sources for each brief lived in a few supervisors' heads and ate margin.
Finding the right sources for each brief eats fixed-fee margin
A human-approved source map tells the system which inboxes, folders and channels to read in priority order and which never to open; no language model runs. It assembles each brief with a file-and-line citation on every field, re-checked from disk, then pre-screens claims against an approved-claims library. Reviewer feedback is saved per account and enforced in the next version.
- 9 of 9 brief fields carry provenance, and all 66 citations were re-read from disk and verified with 0 failures
- the claims screen raised 4 flags on the first draft, 3 high and 1 medium, and 0 after review
- Approved source map
- Project tracker
- Document store
- Email and team chat inboxes
- Citation verification
- Claims pre-screen
- Approved-claims library
- Account preference memory
- Node.js
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.
-
Pharma marketing
The pharma creative that stopped dying at legal review
creative rejection went from 75% to 10%, and the remaining 10% is rejected over creative differences, not compliance
-
Design studio
The brand system that moved into the client's ChatGPT
admin time tracking down assets went from just under 20 hours a week to an hour or two
-
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