Open igl-brand-kb/audience/profiles/02-donna-seed-keeper.md, find the section headed "Who wears it (Q2, open — Tim's gut pending)", and close the question it asks in writing — "designed for Donna to wear, or for Donna to buy for him?" It was left open on five "husband loves it" quotes from one design. The full Loox review export (J:\My Drive\99_Downloads\reviews.0jn7hQ_wPY (2).csv, 921 reviews, 2024-08-31 to 2026-07-09) answers it: 103 reviews name a man as the wearer, and 80 of those 103 are size L, XL or 2XL. Write that in and mark Q2 closed as "buying-for-him is a standing lane, not an edge case."
Then do the cheap half. 26 designs outside the bird-feeder family already carry a man-as-wearer review (full list below). For those 26 product pages, add one male-model mockup in XL as the second product image. Nothing else changes — no new design, no new collection, no new ad. Re-run the count at the quarterly persona re-validation already scheduled in igl-brand-kb/audience/who-data-map.md (line 70, "Re-validate quarterly"), using the same export.
The persona file wrote down a question about who actually wears the shirt and left it open, because the evidence it was built from — ad comments, community stories, Facebook voice — had five instances; the review corpus it never opened has 103.
The seed was a Skool lesson about turning a video into an ebook, and its real subject is not publishing — it is the fact-check step. Every claim from the draft gets a verdict and evidence checked against a corpus the author did not use, and that report, not the article, is the single human checkpoint: "You give it a URL. You read the fact-check report. You approve." (agentic-academy-kb/lessons/00-youtube-to-ebook.md, line 105.)
IGL's persona dossiers are exactly that draft. 02-donna-seed-keeper.md declares status: CURRENT SoR and lists its evidence in the header — ad comments, community stories, Facebook voice, a sales cluster. The review export is not on that list. So when the file reached the question of who wears the shirt, it had a handful of quotes and honestly wrote the question down as open rather than guessing. Run the same claim against the corpus it skipped and the answer arrives with a size distribution attached, which quotes alone could never produce: 78% of man-as-wearer reviews are L/XL/2XL, against a store-wide top three of L (229), XL (187), M (134).
The sharpest single line in the corpus is a one-star review on Quietly Plotting My Next Tomato Harvest: "the shirt so short it was barely long enough for me, a woman just over five feet tall. I wanted the shirt for my six foot son." Nugget #022 established that IGL's own reviews complain shirts run too long; this is the same garment failing in the opposite direction for the buyer this nugget is about. Both are true, and they are two different people.
No single shelf could reach this. The Skool lesson supplies the method (claim → verdict → evidence, against a corpus the author skipped). The brand base supplies the claim and the flag that it was unresolved. The mastermind base supplies why concentration matters commercially: Antonio Rodriguez's profile names "over-concentration of ad spend on a single design" as the root cause that took his week down (line 76) — and 72 of the 103 man-as-wearer reviews sit on the bird-feeder family, the same design that is already 364 of all 921 reviews (39.5%). He also ran a "Who are you shopping for?" popup before Black Friday 2025 where roughly 50% answered "for someone else" (line 85).
Honest limit: these are review counts, not sales. The thirteen knowledge bases hold no product-level sales data, so this measures who shows up in review text, not units shipped. The corpus itself sits outside the knowledge bases, in Tim's Drive folder.
agentic-academy-kb/lessons/00-youtube-to-ebook — the seed. Supplies the mechanic: a fact-check phase that checks every claim against a corpus the author did not use, and stops for a human. Lines 98 and 105.igl-brand-kb/audience/profiles/02-donna-seed-keeper — status: CURRENT SoR, created 2026-08-29. Line 149 is the open question; line 151 is the "five husband loves it" it rests on. The header's evidence list does not include reviews.igl-brand-kb/community/customer-reviews-q4-2025 — the knowledge base's own copy of the corpus, export date December 11 2025, 551 reviews. Nine months stale and 370 rows short of the live export; the man-as-wearer reviews are in it but were never counted.wescale-kb/members/antonio-rodriguez — line 76, "over-concentration of ad spend on a single design" as a standing cohort lesson; line 85, the "Who are you shopping for?" popup at roughly 50% "for someone else".igl-brand-kb/audience/voice/etsy-review-mining-2026-08-30 — the same gift-chain shape on a different platform ("my hubby loves it and wears it every week"), so the share is not an artifact of one review app.igl-brand-kb/audience/who-data-map — line 31 names this exact export and its 921 rows; line 70 schedules the quarterly re-validation the move hangs on.