You asked
How do I setup the game?
Answered counted as answeredAsked with: Power Gridbg-2651-en-1e
To setup the game, follow these steps: 1. Place the board in the middle of the table [1]. 2. For the first game, it is suggested to choose Germany [1]. 3. Choose a contiguous playing zone of connected areas based on the number of players; this serves as the playing zone for all players [1]. 4. Each player takes 50 Elektro, a payment summary card, and all 22 houses of one color [1]. 5. Each player places one of their houses on space 0 of the scoring track for connected cities [1]. 6. Randomly determine the player order by placing one house from each player, one after the other, on the top row of the player order track [1]. 7. Place the remaining resource tokens as a supply near the resource market [2]. 8. Place money separated by value next to the game board [2]. 9. If playing the USA map, place a storage space for coal next to the resource market; at the start of the game, this space is empty because all coal tokens are placed on the spaces of the resource market [2]. 10. Place the appropriate resource refill summary card next to the resource market [2]. 11. Shuffle the pile of power plant cards with a plug on the back (numbered '03' to '15') [2]. 12. Draw the top 8 cards from the shuffled plug-back pile and place them face up on the power plant market; sort them in ascending order by number, placing the four smallest in the top row (current market) and the remaining four in the bottom row (future market), both rows in ascending order, left to right [2]. 13. Take one additional power plant card with a plug on the back face down and set it aside [2]. 14. Set aside the 'Step 3' card, then shuffle the power plant cards with a socket on the back [2]. 15. Depending on the number of players, randomly remove some power plant cards with plugs and sockets from the socket-back pile and place them face down in the box without looking at them [2]. 16. Shuffle all remaining power plant cards together and place them as a face-down stack next to the power plant market (the plug on the back of the top card indicates it is a weaker one) [2]. 17. Place the 'Step 3' card face down under the supply stack, then take the previously set-aside power plant with a plug on the back and place it face-down on top of the supply stack [2]. 18. Place the auction hammer and discount token next to the power plant market [2]. 19. If playing with The Trust, provide space for it next to the game board; The Trust receives 16 houses of its own color plus one additional house for player order, but no money [3]. 20. For a two-player game with The Trust, randomly determine the first player and place one of their houses on space 1 of the player order, then place the other player's house on space 3; The Trust is always second in player order [3]. 21. If playing with The Trust, choose 3 adjacent areas for the playing zone, then place 6 Trust houses on the number 10 spaces of 6 adjacent cities by alternating turns between the starting player and the other player [3]. 22. Place the remaining 10 houses of The Trust as a supply next to the game board [3].
🔧 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 321 ms · ask 11781 ms · total 12114 ms
- single-flight (PR-5)
- queued 0 ms · generation 12114 ms
- retrieval refs (raw)
- [{"page": 3, "score": 0.047643, "snippet": "Place the remaining resource tokens as a supply near the resource market. Place the money separated by value next to the game board. USA map: There is a storage space for coal next to the resource market. At the beginning of the game, this storage space is empty, as all coal tokens are placed on the", "headingPath": "Preparation", "sharpsignalDocId": 94}, {"page": 9, "score": 0.032787, "snippet": "The Trust needs its own space next to the game board, where it places its own power plants. The Trust gets 16 houses of its own color, plus one additional house for player order (The trust does not place a house on the scoring track for connected cities). The Trust does not get any money. Randomly d", "headingPath": "Preparation", "sharpsignalDocId": 94}, {"page": 7, "score": 0.032258, "snippet": "The game runs through three Steps and begins with Step 1. Step 2 begins when the first player has connected a certain number of cities in their network. Step 3 begins after the Step 3 card is drawn from the power plant stack. The game usually ends in Step 3, but in some cases may end in Step 2. This", "headingPath": "The 3 Steps of the Game", "sharpsignalDocId": 94}, {"page": 2, "score": 0.031746, "snippet": "Place the board in the middle of the table. For the first game we suggest choosing Germany. The map is separated into 6 areas, each with 7 cities. In each game, players choose a contiguous playing zone of connected areas depending on the number of players. This is the whole playing zone for ALL play", "headingPath": "Preparation", "sharpsignalDocId": 94}, {"page": 4, "score": 0.030769, "snippet": "Players determine the player order for the round. The first player is the player with the most cities in their network (the house on the highest numbered space of the scoring track for connected cities). If two or more players are tied for the most cities, the first player is the player among them w", "headingPath": "Phase 1: Determine Player Order", "sharpsignalDocId": 94}, {"page": 3, "score": 0.030303, "snippet": "Resource refill for 5 players 04.07.2018 18:11:54 Uhr | | Power plant with plug on the back | Power plant with socket on the back | | 2 players | 1 | 5 | | 3 players | 2 | 6 | | 4 players | 1 | 3 | | 5-6 players | None | None | Place the auction hammer and discount token next to the power plant mark", "headingPath": "Preparation", "sharpsignalDocId": 94}, {"page": 5, "score": 0.029851, "snippet": "The player purchases the resource tokens from the spaces of the resource market. The printed number on the upper right of each resource space shows the price for one resource token. The player pays this amount to the bank for each token. They move their house on the player order track to the same nu", "headingPath": "b. Pass the auction", "sharpsignalDocId": 94}, {"page": 10, "score": 0.029412, "snippet": "During Step 1 of the game, players cannot connect to the six cities, where the players placed the Trust's houses on the spaces numbered 10 during the preparation. These cities are only available when Step 2 of the game starts. As long as the Trust has houses in its supply, each time a player connect", "headingPath": "Phase 4: Building Houses", "sharpsignalDocId": 94}]
- citations (raw)
- [{"page": 2, "quote": null, "headingPath": "Preparation", "sharpsignalDocId": 94}, {"page": 3, "quote": null, "headingPath": "Preparation", "sharpsignalDocId": 94}, {"page": 9, "quote": null, "headingPath": "Preparation", "sharpsignalDocId": 94}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 94 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 94 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 3, 2026 16:00
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 Power Grid — Rulebook (corpus doc 94) | Preparation | p.3 | 0.047643 (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 Power Grid — Rulebook (corpus doc 94) | Preparation | p.9 | 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 Power Grid — Rulebook (corpus doc 94) | The 3 Steps of the Game | p.7 | 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 |
| #4 | RULEBOOK Power Grid — Rulebook (corpus doc 94) | Preparation | p.2 | 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 |
| #5 | RULEBOOK Power Grid — Rulebook (corpus doc 94) | Phase 1: Determine Player Order | 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 |
| #6 | RULEBOOK Power Grid — Rulebook (corpus doc 94) | Preparation | p.3 | 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 Power Grid — Rulebook (corpus doc 94) | b. Pass the auction | p.5 | 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 Power Grid — Rulebook (corpus doc 94) | Phase 4: Building Houses | p.10 | 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 Power Grid — Rulebook (corpus doc 94) | Preparation | p.2 | no quote on the wire |
| [2] | RULEBOOK Power Grid — Rulebook (corpus doc 94) | Preparation | p.3 | no quote on the wire |
| [3] | RULEBOOK Power Grid — Rulebook (corpus doc 94) | Preparation | p.9 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 321 ms · first delta 6528 ms · total 12114 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 321 ms · ask 11781 ms · gateway work 12114 ms · total 12114 ms
- tokens in (the prompt the answerer read)
- 3294
- tokens out (what the answerer generated)
- 753
- tok/sec
- 135.9 tok/sec — 753 output tokens in 5.539 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 48s 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 25), 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.