You asked
How do I set up the game?
Answered counted as answeredAsked with: Sagradabg-199561-en-1e
To set up the game, follow these steps: 1. Give each player a Player Board and matching Score Marker [1]. 2. Give each player 2 Window Pattern Cards at random [1]. 3. Give each player 1 Private Objective Card at random; players must secretly look at their card and place it face-down [1]. 4. Players choose one of their four window patterns (from the fronts and backs of both cards) [1]. 5. Players take the number of Favor Tokens indicated on the chosen window pattern's bottom right [1]. 6. Players slide the chosen window pattern card into the bottom of their Player Board, with the selected side facing forward [1]. 7. Place the Score Marker near the Round Track [1]. 8. Place the Round Track near the center of the play area [1]. 9. Shuffle the Tool Cards and place 3 face-up near the Round Track [1]. 10. Shuffle the Public Objective Cards and place 3 face-up near the Round Track [1]. 11. Put the appropriate number of dice in the Dice Bag and shake them: - 2 Players: 50 dice (10 of each color) [1] - 3 Players: 70 dice (14 of each color) [1] - 4 Players: All 90 dice [1] 12. Set aside all other cards, dice, and components not used during the game [1]. 13. Choose a Start Player (e.g., the player wearing the most colorful clothes or via random selection) and give them the Dice Bag [1].
🔧 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 277 ms · ask 5665 ms · total 1954570 ms
- single-flight (PR-5)
- queued 1948619 ms · generation 5951 ms
- retrieval refs (raw)
- [{"page": 3, "score": 0.04918, "snippet": "A 1 Player Board and matching Score Marker B C 2 Window Pattern Cards at random D 1 Private Objective Card at random Secretly looks at their Private Objective Card D and places it face-down. Chooses one of their four window patterns C (from the fronts and backs of both cards). Takes the number of Fa", "headingPath": "Give each player: · Each player: · GAME SETUP 2", "sharpsignalDocId": 185}, {"page": 7, "score": 0.047875, "snippet": "When playing solo, you'll take on the Old Master, who uses your discarded glass to make a masterpiece of their own. The Old Master's score is the sum of the values from all the dice on the Round Track at the end of the game. Beat their score to win! Set up the game as usual for 2 players with one ex", "headingPath": "SOLO PLAY: DEFEAT THE OLD MASTER · SET UP · GAMEPLAY · CREDITS · END OF ROUND", "sharpsignalDocId": 185}, {"page": 5, "score": 0.047123, "snippet": "As an example, a can be placed in any of the spaces but may not be placed in any of the spaces. The remaining spaces are off limits because each die must be placed adjacent to another die. TIP: When choosing where to place your die, pay careful attention to color or value requirements adjacent to th", "headingPath": "PLACING DICE (CONTINUED) · TOOL CARDS & FAVOR TOKENS · END OF ROUND", "sharpsignalDocId": 185}, {"page": 6, "score": 0.045037, "snippet": "Clear all the dice from the Round Track and flip it over to the Score Track side. Count up players' points with their Score Markers (flipping it over to the '50' side if they exceed 50 points). Public Objective Cards: Gain the indicated Victory Points (VP) for dice in your window that meet the requi", "headingPath": "END OF GAME · SCORING · TIEBREAKERS · SCORING EXAMPLE", "sharpsignalDocId": 185}, {"page": 4, "score": 0.032258, "snippet": "Sagrada is played over 10 rounds. In each round, the Start Player pulls dice from the Dice Bag at random and rolls them to form the Dice Pool. The number of dice pulled depends on the number of players-2 dice per player + 1 additional die. 2 players - 5 dice 3 players - 7 dice 4 players - 9 dice Pla", "headingPath": "HOW TO PLAY 3 · DICE PLACEMENT RULES · WINDOW PATTERN REQUIREMENTS · The Golden Rule of Sagrada", "sharpsignalDocId": 185}, {"page": 4, "score": 0.030769, "snippet": "Even the most accomplished artisans can make an error or two. If you realize that you've broken a dice placement rule (such as placing two dice of the same color or number next to each other), at any point of the game, you must immediately remove dice of your choice from your window until all requir", "headingPath": "DICE PLACEMENT MISTAKES", "sharpsignalDocId": 185}, {"page": 7, "score": 0.030303, "snippet": "At the end of the 10th round, add up the Old Master's score by tallying up the value of all dice on the Round Track. Add up your score as normal with one exception: For each empty space in your window, LOSE 3 VICTORY POINTS. If your score is higher than the Old Master's, you win! Playtesting: Nikhil", "headingPath": "END OF GAME SCORING", "sharpsignalDocId": 185}, {"page": 1, "score": 0.029851, "snippet": "A Brilliant Puzzle Game of Dice, Light, and Color 1 TO 4 PLAYERS - 30 MINUTES SKIP THE RULES, LEARN TO PLAY HERE: floodgate.games/learn-sagrada The glaziers of the Sagrada Familia understand the beautiful puzzle that lies at the heart of the world's most breathtaking stained glass.", "headingPath": "", "sharpsignalDocId": 185}]
- citations (raw)
- [{"page": 3, "quote": null, "headingPath": "Give each player: · Each player: · GAME SETUP 2", "sharpsignalDocId": 185}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 185 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 185 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 14:43
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 Sagrada — Rulebook (corpus doc 185) | Give each player: · Each player: · GAME SETUP 2 | p.3 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | 300 |
| #2 | RULEBOOK Sagrada — Rulebook (corpus doc 185) | SOLO PLAY: DEFEAT THE OLD MASTER · SET UP · GAMEPLAY · CREDITS · END OF ROUND | p.7 | 0.047875 (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 Sagrada — Rulebook (corpus doc 185) | PLACING DICE (CONTINUED) · TOOL CARDS & FAVOR TOKENS · END OF ROUND | p.5 | 0.047123 (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 Sagrada — Rulebook (corpus doc 185) | END OF GAME · SCORING · TIEBREAKERS · SCORING EXAMPLE | p.6 | 0.045037 (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 Sagrada — Rulebook (corpus doc 185) | HOW TO PLAY 3 · DICE PLACEMENT RULES · WINDOW PATTERN REQUIREMENTS · The Golden Rule of Sagrada | p.4 | 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 |
| #6 | RULEBOOK Sagrada — Rulebook (corpus doc 185) | DICE PLACEMENT MISTAKES | p.4 | 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 |
| #7 | RULEBOOK Sagrada — Rulebook (corpus doc 185) | END OF GAME SCORING | p.7 | 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 |
| #8 | RULEBOOK Sagrada — Rulebook (corpus doc 185) | 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)) | 282 |
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 Sagrada — Rulebook (corpus doc 185) | Give each player: · Each player: · GAME SETUP 2 | p.3 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 277 ms · first delta 3352 ms · total 1954570 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 1948619 ms · retrieval 277 ms · ask 5665 ms · gateway work 5951 ms · total 1954570 ms
- tokens in (the prompt the answerer read)
- 2806
- tokens out (what the answerer generated)
- 353
- tok/sec
- 138.6 tok/sec — 353 output tokens in 2.547 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 13s 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)
-
set up
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 103), 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.