You asked
How do I setup the game?
Answered counted as answeredAsked with: Brass: Birminghambg-224517-en-1e
1. Place the board on either the day or night side [1]. 2. For a player count of less than 4, remove all cards and Merchant tiles that show a player count greater than your number of players, and return them to the box [1]. 3. Separate the Wild Location and Wild Industry cards and place them face up on 2 of the Card Draw Areas [1]. 4. Shuffle the remaining cards and place them face down on the remaining Card Draw Area; this is the Draw Deck [1]. 5. Shuffle the remaining Merchant tiles, and place 1 (face up) on each of the Merchant spaces marked with the number of players in your game, located near the edges of the board [1]. 6. Place 1 beer barrel on each beer barrel space beside a (non-blank) Merchant tile [1]. 7. Place 1 black cube on each space of the Coal Market, leaving 1 of the £ 1 spaces open [1]. 8. Place 1 orange cube on each space of the Iron Market, leaving both of the £ 1 spaces open [1]. 9. Place the remaining cubes and beer barrels beside the board; this is the General Supply [1]. 10. Take a Player Mat [2]. 11. Take £ 17 from the Bank [2]. 12. Choose a coloured Character tile [2]. 13. Place the matching coloured Link tiles in your player area in their appropriate slots on your Player Mat, with the side of the tiles face down [2]. 14. Place your Victory Point (VP) Marker on the '0' space of the Progress Track [2]. 15. Place your Income Marker on the '10' space of the Progress Track [2]. 16. Draw 8 cards from the Draw Deck; this is your Hand, and do not reveal your Hand to other players [2]. 17. Draw 1 additional card from the Draw Deck and place it face down in your player area; this is your Discard Pile [2]. 18. Stack the matching coloured Industry tiles (Cotton Mills, Coal Mines, Iron Works, Manufacturers, Potteries, and Breweries) with the black top half face down [2]. 19. After all players have set up their player area, shuffle all players' Character tiles together and place them in a random order on the Turn Order Track [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 394 ms · ask 8588 ms · total 8993 ms
- single-flight (PR-5)
- queued 0 ms · generation 8993 ms
- retrieval refs (raw)
- [{"page": 3, "score": 0.048652, "snippet": "Place the board on either the day or night side. For a player count of less than 4, remove all cards and Merchant tiles that show a player count greater than your number of players, and return them to the box. The 2-player ( ), 3-player ( ), and 4-player ( ) counts are shown in the bottom right corn", "headingPath": "BOARD SETUP", "sharpsignalDocId": 86}, {"page": 3, "score": 0.032787, "snippet": "Take a Player Mat. Take £ 17 from the Bank . Choose a coloured Character tile. Q Place the matching coloured Link tiles in your player area . their appropriate slots on your Player Mat. The side of the tiles face down. Place your Victory Point (VP) Marker on the '0' space of the Progress Track X . P", "headingPath": "PLAYER AREA SETUP", "sharpsignalDocId": 86}, {"page": 5, "score": 0.031746, "snippet": "Take the lowest level tile L of the chosen industry from your Player Mat and place it (the side with the black top half face down) on an undeveloped space in your chosen build location, obeying the following rules: If possible, place it on a space displaying only that industry's icon M . Otherwise, ", "headingPath": "Moving Coal and Iron to the Market", "sharpsignalDocId": 86}, {"page": 4, "score": 0.03125, "snippet": "Rearrange the Character tiles on the Turn Order Track. The player who spent the least money this round will go first next round B , and so on, while the player who spent the most will go last C . If multiple players have spent an equal amount, their relative turn order remains the same C . Afterward", "headingPath": "Determine turn order for the next round", "sharpsignalDocId": 86}, {"page": 6, "score": 0.030769, "snippet": "Discard any card from your Hand, and place it face up onto your Discard Pile. Exception: Wild cards are placed back onto their Card Draw Area. Place a Link tile on an undeveloped line on the board H . The placed Link tile must be adjacent to a location that is a part of your network (see 'Your Netwo", "headingPath": "To perform the Network action:", "sharpsignalDocId": 86}, {"page": 4, "score": 0.030303, "snippet": "On your turn, perform a total of 2 actions. Exception: During the first round of the Canal Era, each player performs only 1 action. For each action you perform, you must discard a card from your Hand and place it face up on top of your Discard Pile. Exception: Wild cards are placed back onto their C", "headingPath": "PLAYER TURNS", "sharpsignalDocId": 86}, {"page": 4, "score": 0.029851, "snippet": "For each action, you may choose to perform one of the following (you may perform the same action twice): Build - Place one of your Industry tiles onto the board, paying the appropriate cost and consuming any required coal / iron. Note: Only Build requires a specific card. Network - Expand your canal", "headingPath": "ACTIONS LIST", "sharpsignalDocId": 86}, {"page": 6, "score": 0.029412, "snippet": "Discard any card from your Hand, and place it face up onto your Discard Pile. Exception: Wild cards are placed back onto their Card Draw Area.", "headingPath": "To perform the Develop action:", "sharpsignalDocId": 86}]
- citations (raw)
- [{"page": 3, "quote": null, "headingPath": "BOARD SETUP", "sharpsignalDocId": 86}, {"page": 3, "quote": null, "headingPath": "PLAYER AREA SETUP", "sharpsignalDocId": 86}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 86 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 86 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 2, 2026 09:32
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 Brass: Birmingham — Rulebook (corpus doc 86) | BOARD SETUP | p.3 | 0.048652 (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 Brass: Birmingham — Rulebook (corpus doc 86) | PLAYER AREA SETUP | 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 |
| #3 | RULEBOOK Brass: Birmingham — Rulebook (corpus doc 86) | Moving Coal and Iron to the Market | p.5 | 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 Brass: Birmingham — Rulebook (corpus doc 86) | Determine turn order for the next round | p.4 | 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 Brass: Birmingham — Rulebook (corpus doc 86) | To perform the Network action: | p.6 | 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 Brass: Birmingham — Rulebook (corpus doc 86) | PLAYER TURNS | 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 Brass: Birmingham — Rulebook (corpus doc 86) | ACTIONS LIST | p.4 | 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 Brass: Birmingham — Rulebook (corpus doc 86) | To perform the Develop action: | p.6 | 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)) | 142 |
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 Brass: Birmingham — Rulebook (corpus doc 86) | BOARD SETUP | p.3 | no quote on the wire |
| [2] | RULEBOOK Brass: Birmingham — Rulebook (corpus doc 86) | PLAYER AREA SETUP | p.3 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 394 ms · first delta 5263 ms · total 8993 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 394 ms · ask 8588 ms · gateway work 8993 ms · total 8993 ms
- tokens in (the prompt the answerer read)
- 1868
- tokens out (what the answerer generated)
- 513
- tok/sec
- 139.1 tok/sec — 513 output tokens in 3.689 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 44s 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 17), 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.