This week, brief ONE render: the existing "Excuse Me, Bird Feeder's Empty" shirt with the squirrel replaced by a raccoon — same layout, same lettering, same joke, only the animal changes. Then deer, then bear, in that order. Do NOT make "a raccoon shirt": you have made nine of those and they have sold 37 units between them, six of them zero. Frame the raccoon as a character with an attitude, not a thief — the current voice line in igl-brand-kb/core/brand-guide-from-inside-out.md:98 is "the raccoons had other plans," and the raccoon character card says DON'T portray as villain, while the customers asking are framing it as the robber ("they empty ours lol"). Then add G:\iris\igl-ads\scripts\pull-ad-comments.py as a step in the MasterWeekly Windows task you already run (next fires Saturday 2026-09-19 4:04 AM), so the request list refreshes weekly instead of sitting frozen at the 2026-08-04 pull.
IGL has answered "make it a raccoon" six times by linking an existing raccoon graphic tee, and the same request kept arriving anyway — because nobody is asking for a raccoon, they are asking for this joke with a raccoon in it, and that shirt has never been made.
WeScale call #34 floats a comment-to-design pipeline as a concept — scrape the Facebook comment requests, feed them back through the design pipeline, repost — and Chris tells the room to validate it by hand first, because he found thousands of requests in his own archive (wescale-kb/calls/call-34.md:39). IGL's archive is already pulled and sitting in a JSON file. It has been mined twice — once for voice, once for drawing defects (nugget #035) — and never once for the thing Chris actually described.
Run it over the whole corpus and the concentration is extreme. Of 1,722 ad posts, only 196 ever received a comment, and 1,252 comments — 39.0% of every comment IGL's ads have ever collected — sit on ten posts for one design, the bird feeder shirt. Hand-classify every comment naming an animal and the request order is raccoon 7, deer 5, bear 1. (On raw mentions bear 9 edges deer 8, but seven of those nine bears are people telling bear stories, not asking for a shirt. Requests are the honest unit, and on requests the order holds.)
Here is the part no judge reached, and the reason this is not "make more animal variants." IGL already sells nine raccoon shirts. Across all nine, lifetime: 37 units, $1,166.79 — 0.33% of the store. Six of them, every one created in 2026, have sold zero. And six times between January and June 2025, a request for a raccoon was answered in-thread with a link to one of those existing raccoon tees — four of them within a day of the ask. The asks kept coming after each reply. The existing raccoon shirt is not a near-miss on the request; it is an answer to a different question. The bird feeder family, over the same measured period, is 4,322 units and $137,613.52 — 38.8% of all store units.
That distinction is where the two sources collide. The mastermind's answer to a slow week is breadth — call #34 line 38, "100 designs/week is not too many." Todd Graves built Raising Cane's on the opposite instinct and is explicit about the pressure he refused: the chains around him kept adding menu items to dodge the "veto vote," he studied In-N-Out ("since 1948, they have the exact same menu") and concluded "you can do one thing and do it better than anybody else." He draws the line that matters here too — "it's not simple. It's focused." A raccoon version of the bird feeder shirt is In-N-Out's animal style: a variation on the one item people already come for. Nine unrelated raccoon shirts are the veto-vote menu.
No single shelf produces this. The mastermind supplies the mechanism and the instruction to hand-validate it. A 2025 restaurant interview supplies the discipline that says spend the variation on the proven item. Only IGL's own comment archive says which animal. And only the sales database says the obvious objection — "we already have raccoon shirts" — is exactly the mistake.
wescale-kb/calls/call-34 — SEED. Dated 2026-06-18, a call record. Supplies the comment-to-design pipeline concept and Chris's "validate by hand first" instruction (line 39), and the competing volume doctrine, "100 designs/week is not too many" (line 38).founders-kb/interviews/004-todd-graves-transcript — THE BRAID. 2025 interview, different era and trade. The "veto vote" pressure, In-N-Out's unchanged 1948 menu, "you can do one thing and do it better than anybody else," and "it's not simple. It's focused." All verified verbatim.igl-brand-kb/methodology/design-flywheel-framework — Status: CURRENT SoR, filed 2026-03-03. Line 127: the only raccoon idea in current methodology is a text shirt, "small raccoon silhouette bottom corner" — not the illustration swap 7 customers asked for. This is the gap the nugget closes.igl-brand-kb/core/brand-identity-guide-v9 — Status: HISTORICAL, compiled August 2025, superseded February 2026, and cited as historical. Line 446, character card "Ross — Ninja Raccoon … DON'T: Portray as villain." The routing constraint on the render. The current voice docs agree: "the raccoons had other plans" is affectionate (core/brand-guide-from-inside-out.md:98, voice/voice-guidelines.md:44).igl-brand-kb/audience/profiles/05-carol-garden-witness — buyer profile, independent corroboration from a non-ad source: "feeders in at night (raccoons), ammonia on the baffle (bears)." Persona research and ad comments name the same animals.igl-brand-kb/audience/who-data-map — theme-aggregate, the one permitted. Line 30 locates the corpus and dates it: 3,210 comments (2,124 unique), harvester re-runnable, pulled 2026-08-04 — six weeks stale as of tonight. Sources outside the knowledge bases, named as such: the comment archive G:\iris\igl-ads\data\ad-comments-2026-08-04.json and the operational database G:\iris\igl-ops-sage\data\igl.db. The thirteen knowledge bases hold no product-level sales data, so every unit and dollar figure above is an operator query of a database outside them, measured through 2026-09-13 — not a document quotation.igl-brand-kb/core/brand-guide-from-inside-out.md:98 is "the raccoons had other plans," and the raccoon character card says DON'T portray as villain, while the customers asking are framing it as the robber ("they empty ours lol"). Then add G:\iris\igl-ads\scripts\pull-ad-comments.py as a step in the MasterWeekly Windows task you already run (next fires Saturday 2026-09-19 4:04 AM), so the request list refreshes weekly instead of sitting frozen at the 2026-08-04 pull. ## Why (the one-liner) IGL has answered "make it a raccoon" six times by linking an existing raccoon graphic tee, and the same request kept arriving anyway — because nobody is asking for a raccoon, they are asking for this joke with a raccoon in it, and that shirt has never been made. ## The insight WeScale call #34 floats a comment-to-design pipeline as a concept — scrape the Facebook comment requests, feed them back through the design pipeline, repost — and Chris tells the room to validate it by hand first, because he found thousands of requests in his own archive (wescale-kb/calls/call-34.md:39). IGL's archive is already pulled and sitting in a JSON file. It has been mined twice — once for voice, once for drawing defects (nugget #035) — and never once for the thing Chris actually described. Run it over the whole corpus and the concentration is extreme. Of 1,722 ad posts, only 196 ever received a comment, and 1,252 comments — 39.0% of every comment IGL's ads have ever collected — sit on ten posts for one design, the bird feeder shirt. Hand-classify every comment naming an animal and the request order is raccoon 7, deer 5, bear 1. (On raw mentions bear 9 edges deer 8, but seven of those nine bears are people telling bear stories, not asking for a shirt. Requests are the honest unit, and on requests the order holds.) Here is the part no judge reached, and the reason this is not "make more animal variants." IGL already sells nine raccoon shirts. Across all nine, lifetime: 37 units, $1,166.79 — 0.33% of the store. Six of them, every one created in 2026, have sold zero. And six times between January and June 2025, a request for a raccoon was answered in-thread with a link to one of those existing raccoon tees — four of them within a day of the ask. The asks kept coming after each reply. The existing raccoon shirt is not a near-miss on the request; it is an answer to a different question. The bird feeder family, over the same measured period, is 4,322 units and $137,613.52 — 38.8% of all store units. That distinction is where the two sources collide. The mastermind's answer to a slow week is breadth — call #34 line 38, "100 designs/week is not too many." Todd Graves built Raising Cane's on the opposite instinct and is explicit about the pressure he refused: the chains around him kept adding menu items to dodge the "veto vote," he studied In-N-Out ("since 1948, they have the exact same menu") and concluded "you can do one thing and do it better than anybody else." He draws the line that matters here too — "it's not simple. It's focused." A raccoon version of the bird feeder shirt is In-N-Out's animal style: a variation on the one item people already come for. Nine unrelated raccoon shirts are the veto-vote menu. No single shelf produces this. The mastermind supplies the mechanism and the instruction to hand-validate it. A 2025 restaurant interview supplies the discipline that says spend the variation on the proven item. Only IGL's own comment archive says which animal. And only the sales database says the obvious objection — "we already have raccoon shirts" — is exactly the mistake. ## Evidence trail - wescale-kb/calls/call-34 — SEED. Dated 2026-06-18, a call record. Supplies the comment-to-design pipeline concept and Chris's "validate by hand first" instruction (line 39), and the competing volume doctrine, "100 designs/week is not too many" (line 38). - founders-kb/interviews/004-todd-graves-transcript — THE BRAID. 2025 interview, different era and trade. The "veto vote" pressure, In-N-Out's unchanged 1948 menu, "you can do one thing and do it better than anybody else," and "it's not simple. It's focused." All verified verbatim. - igl-brand-kb/methodology/design-flywheel-framework — Status: CURRENT SoR, filed 2026-03-03. Line 127: the only raccoon idea in current methodology is a text shirt, "small raccoon silhouette bottom corner" — not the illustration swap 7 customers asked for. This is the gap the nugget closes. - igl-brand-kb/core/brand-identity-guide-v9 — Status: HISTORICAL, compiled August 2025, superseded February 2026, and cited as historical. Line 446, character card "Ross — Ninja Raccoon … DON'T: Portray as villain." The routing constraint on the render. The current voice docs agree: "the raccoons had other plans" is affectionate (core/brand-guide-from-inside-out.md:98, voice/voice-guidelines.md:44). - igl-brand-kb/audience/profiles/05-carol-garden-witness — buyer profile, independent corroboration from a non-ad source: "feeders in at night (raccoons), ammonia on the baffle (bears)." Persona research and ad comments name the same animals. - igl-brand-kb/audience/who-data-map — theme-aggregate, the one permitted. Line 30 locates the corpus and dates it: 3,210 comments (2,124 unique), harvester re-runnable, pulled 2026-08-04 — six weeks stale as of tonight. Sources outside the knowledge bases, named as such: the comment archive G:\iris\igl-ads\data\ad-comments-2026-08-04.json and the operational database G:\iris\igl-ops-sage\data\igl.db. The thirteen knowledge bases hold no product-level sales data, so every unit and dollar figure above is an operator query of a database outside them, measured through 2026-09-13 — not a document quotation. ## Assay verdicts - novelty — PASS (3). competitors-kb/concept-formulas.md F9 "The creature's complaint" canonizes the form and states "the ladder (species × complaint × season) has never been run," so the build is assigned work; which animal, derived from IGL's own archive, plus the villain constraint, appears nowhere. Nugget #035 read the same file as a defect log and explicitly set the request comments aside. Held at 3, not higher. - grounding — PASS (5). The judge independently re-ran the analysis on the raw file: 1,722 stories, 196 with comments, 3,210 comments — all exact; the animal counts reproduced within one. - actionability — PASS (5). One render, one variable changed, a named order, a counted justification, a brand constraint, and a one-line addition to a task that already runs. Operator corrections applied to the hunt's version (all four verified on disk): 1. The nine existing raccoon shirts and their 37 units were missing entirely. Added, and they invert the move from "brief a raccoon" to "brief this joke with a raccoon." 2. "Raccoon by a factor of three over the next candidate" — wrong. Next on raw mentions is rat at 15, so the true factor is 1.8x. Restated on requests, where it is 7 to 5. 3. The order raccoon → deer → bear holds on requests (7/5/1) but not on raw mentions, where bear 9 edges deer 8. Stated on the unit that supports it. 4. The animal enumeration was incomplete: hummingbird (6) outranks the chipmunk (5) the hunt did list. Full list now runs squirrel 170, raccoon 27, rat 15, bear 9, deer 8, hummingbird 6, chipmunk 5, dog 4, cat 3, blue jay 2, woodpecker 2, opossum 2, groundhog 1, rabbit 1. Thread: call-34 comment-to-design pipeline → Todd Graves (one item, In-N-Out's 1948 menu) → IGL's 3,210-comment ad archive, hand-classified tonight for requests → the nine raccoon shirts in igl.db that answer a different question → design-flywheel's text-only raccoon → brand-identity-guide's "don't portray as villain" → carol-garden-witness names the same animals