You asked
Walk me through the full setup procedure step by step.
Answered counted as answeredAsked with: Tapestrybg-286096-en-1e
1. Place the board on the table (big map for 4-5 players; small map for 1-3) [1]. 2. Shuffle the tech cards, place the deck face down next to the board, and reveal 3 cards [1]. 3. Shuffle the tapestry cards and place the deck face down next to the board [1]. 4. Shuffle the territory tiles and place them in face-down stacks next to the board [1]. 5. Do the same with the space tiles [1]. 6. Place landmark miniatures on top of the matching slots on the landmark board; extra landmarks go near the tech card deck [1]. 7. Place the science die (green) near the science track and the conquer dice (red and black) near the military track [1]. 8. Claim a random capital city mat and sit near it (in 1-3 player games, pair up mats based on board numbers, choose one, and discard the other) [2]. 9. Place 2 outpost tokens in your player color on the territory on the map matching the number of your capital city; keep the other 8 outpost tokens off to the side of your income mat [2]. 10. Seed each resource track on your income mat with the corresponding building (5 brown farms, 5 grey houses, 5 yellow markets, and 5 red armories) so that the far left space of each row is exposed [2]. 11. Place 1 token for each resource on the 0 space of the resource tracker at the bottom of your mat [2]. 12. Gain 2 random civilization mats, choose 1, and discard the other [2]. 13. Shuffle all unused and discarded civilization mats into a deck [2]. 14. Place 1 player token on each of the 4 advancement track starting spaces (far-left circles on the board) and 1 token on 0 VP; keep extras off to the side [2]. 15. Randomly select the 1st player and begin [2].
🔧 debug — where this ruling came from
- outcome
- ANSWERED — Answered
- corpus profile
- live
- answerer pin (deploy-frozen, attribution only)
- gemma4:26b think:false 5571076f3d70
- timings
- search 269 ms · ask 5815 ms · total 6096 ms
- single-flight (PR-5)
- queued 0 ms · generation 6096 ms
- retrieval refs (raw)
- [{"page": 3, "score": 0.032787, "snippet": "First, gain a tech card, selecting from the faceup cards or the top of the deck. Replenish a face-up card immediately after you gain it. If the deck is empty, reshuffle discarded cards to form a new deck. Second, place the card to the right of your capital city mat in the bottom row. There is no lim", "headingPath": "INVENT · CONQUER", "sharpsignalDocId": 367}, {"page": 2, "score": 0.032258, "snippet": "GAIN THIS BENEFIT Upgrade the Zeppelins tech card to the middle row, then gain the benefit in the circle. Gain 1 VP for each of your tech cards (x2), 1 VP for each completed row and column in your capital city (x3), and 1 VP for each territory you control (x1). Pay any 1 resource and advance your pl", "headingPath": "UPGRADE TECH CARD ( GAIN VICTORY POINTS (", "sharpsignalDocId": 367}, {"page": 3, "score": 0.031746, "snippet": "First, select 1 territory tile from your supply and place it on an unexplored hex adjacent to a territory you control, oriented in any direction: Second, gain 1 VP for each side of the explored territory with at least 1 aligned terrain (water, mountains, desert, etc; max 6 VP). Ignore the 'rivers' b", "headingPath": "EXPLORE · RESEARCH", "sharpsignalDocId": 367}, {"page": 2, "score": 0.03125, "snippet": "Most turns in Tapestry will be used to advance on an advancement track. Follow these steps in order: Pay the cost (the resources indicated under the tier of the track into which you're advancing). Move your player token 1 space forward on the track, then gain the benefit. If available, you may pay t", "headingPath": "ADVANCE · GAMEPLAY · INCOME · USE CIVILIZATION ( if applicable · PLAY A TAPESTRY CARD (", "sharpsignalDocId": 367}, {"page": 1, "score": 0.030769, "snippet": "CAPITAL CITY MAT (x6): Claim a random capital city mat* and sit near it. Place 2 outpost tokens (hexagonal tokens in your player color) on the territory on the map matching the number of your capital city. Your other 8 outpost tokens are kept off to the side of your income mat. * In a 1-3 player gam", "headingPath": "PLAYER SETUP", "sharpsignalDocId": 367}, {"page": 4, "score": 0.030303, "snippet": "When you complete a district by filling all plots in one of the nine indicated 3x3 areas, immediately gain any 1 resource. When scoring your capital city ( ), gain 1 VP for every completed row and column. You may gain and place buildings even if they extend outside of your city grid, as they may not", "headingPath": "OTHER NOTES ABOUT BUILDINGS", "sharpsignalDocId": 367}, {"page": 1, "score": 0.029851, "snippet": "1-5 players; 90-120 minutes; ages 12+; competitive art by Andrew Bosley · sculpts by Rom Brown Create the civilization with the most storied history, starting at the beginning of humankind and reaching into the future. The paths you choose will vary greatly from real-world history-your civilization ", "headingPath": "A Civilization Game · designed by Jamey Stegmaier · GLOBAL SETUP", "sharpsignalDocId": 367}, {"page": 4, "score": 0.029412, "snippet": "Buildings are permanently placed in your capital city to help you (1) complete districts to gain instant resources and (2) complete rows and columns to score victory points. You can place buildings on any open plot in your capital city. Certain plots of land are impassable ( )-you cannot build there", "headingPath": "BUILDINGS & CAPITAL CITIES · THERE ARE 2 CATEGORIES OF BUILDINGS: · OTHER IMPORTANT NOTES · END GAME", "sharpsignalDocId": 367}]
- citations (raw)
- [{"page": 1, "quote": null, "headingPath": "A Civilization Game · designed by Jamey Stegmaier · GLOBAL SETUP", "sharpsignalDocId": 367}, {"page": 1, "quote": null, "headingPath": "PLAYER SETUP", "sharpsignalDocId": 367}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 367 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 367 boosted
- answered-before recall
-
this ruling was answered, so past rulings were not offered
similarity threshold in force: 0.55 (rulesage.answered-before.similarity-threshold; the exact-question tier is not gated by it)
- debug row retained until
- Nov 6, 2026 18:28
retrieval — what the search arm returned
score = the fused retrieval score (reciprocal-rank fusion over the search arms) — NOT a cosine similarity. This ruling ran the THREE-ARM fuse (full-text + vector + the doc-priority boost arm, which carried the base rulebook and/or the errata corrections this query matched), whose arithmetic ceiling is 0.04918 — all three arms ranking the same chunk #1 (ceiling = arms/(k+1) at k=60). The measured healthy band 0.016–0.033 was measured on TWO-arm asks and does not bound this one: its high end is the two-arm ceiling, and a third arm has room above it. A chunk only one arm ranked highly lands near 0.016 (that one arm's #1 vote), so 0.03 here is an excellent hit, not a 3% match.
per-arm ranks (the rank each search arm gave a chunk): NOT DISCLOSED by the gateway. Fusion happens gateway-side and only the FUSED score crosses the wire, so rulesage cannot show them without a gateway change. The rank column below is the FUSED rank (position in the returned list), which is real.
token count per chunk: NOT DISCLOSED — chunk token counts are not reported on the ask path. The character counts below are of the bounded snippet/quote rulesage actually received — a real measurement of what we hold, never an estimate of the chunk.
| fused rank | document | heading | page | fused RRF score | snippet chars |
|---|---|---|---|---|---|
| #1 | RULEBOOK Tapestry — Rulebook (corpus doc 367) | INVENT · CONQUER | p.3 | 0.032787 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #2 | RULEBOOK Tapestry — Rulebook (corpus doc 367) | UPGRADE TECH CARD ( GAIN VICTORY POINTS ( | p.2 | 0.032258 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #3 | RULEBOOK Tapestry — Rulebook (corpus doc 367) | EXPLORE · RESEARCH | p.3 | 0.031746 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #4 | RULEBOOK Tapestry — Rulebook (corpus doc 367) | ADVANCE · GAMEPLAY · INCOME · USE CIVILIZATION ( if applicable · PLAY A TAPESTRY CARD ( | p.2 | 0.03125 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #5 | RULEBOOK Tapestry — Rulebook (corpus doc 367) | PLAYER SETUP | p.1 | 0.030769 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #6 | RULEBOOK Tapestry — Rulebook (corpus doc 367) | OTHER NOTES ABOUT BUILDINGS | p.4 | 0.030303 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #7 | RULEBOOK Tapestry — Rulebook (corpus doc 367) | A Civilization Game · designed by Jamey Stegmaier · GLOBAL SETUP | p.1 | 0.029851 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #8 | RULEBOOK Tapestry — Rulebook (corpus doc 367) | BUILDINGS & CAPITAL CITIES · THERE ARE 2 CATEGORIES OF BUILDINGS: · OTHER IMPORTANT NOTES · END GAME | p.4 | 0.029412 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
chosen chunks — what the answer actually cited
token count per chunk: NOT DISCLOSED — chunk token counts are not reported on the ask path. The character counts below are of the bounded snippet/quote rulesage actually received — a real measurement of what we hold, never an estimate of the chunk.
| # | document | heading | page | quote chars |
|---|---|---|---|---|
| [1] | RULEBOOK Tapestry — Rulebook (corpus doc 367) | A Civilization Game · designed by Jamey Stegmaier · GLOBAL SETUP | p.1 | no quote on the wire |
| [2] | RULEBOOK Tapestry — Rulebook (corpus doc 367) | PLAYER SETUP | p.1 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 269 ms · first delta 2876 ms · total 6096 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 0 ms · retrieval 269 ms · ask 5815 ms · gateway work 6096 ms · total 6096 ms
- tokens in (the prompt the answerer read)
- 3683
- tokens out (what the answerer generated)
- 437
- tok/sec
- 137.5 tok/sec — 437 output tokens in 3.178 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 19s ago)
- stream path
- streamed — the gateway pushed at least one accumulated draft
- watchdog
- first-token watchdog: 30s per arming window (rulesage.table.first-token-watchdog-seconds), re-armed once by the passages frame — so the worst case before a reader falls back to polling is 60s. Whether it actually fired is a BROWSER-side decision that never reaches the server, so it is not recorded here. The stream path above is the server's half of that story: whether a delta was emitted at all.
- num_ctx · think posture
- both are the CHILD's settings, not rulesage's, and no ask reply carries them — an answer never states which context window or think posture produced it. The live-seat line above reads them from the running child instead, where the gateway can answer for itself; it describes the child NOW, not this ask.
disposition
- outcome
- ANSWERED — Answered
- abstain rationale (n/a — this ruling answered)
- answered — no abstain rationale applies
setup-shape — why the checklist band did or didn't render
- decision
- NO_APPROVED_CHECKLIST — setup-shaped, but no approved setup checklist exists for this game
- pattern that matched
- SETUP — "setup" / "set up"
- matched words (in the normalized question)
-
setup
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 296), so "no registered errata card matched" above could never have matched one
Errata scope: the gate above matched this ruling's own edition only. When an ask also reads an expansion, that expansion's own registered errata cards stay outside the match — a stated phase-1 limitation, not a failed lookup.