Ruling — Power Grid

You asked

How do I play?

Answered counted as answered

Asked with: Power Gridbg-2651-en-1e

The game is played over several rounds, which consist of five phases.[1] The game also progresses through three Steps.[1][2]

Phases of a Round

In each phase, all players take their actions in the specified order before the game continues to the next phase.[1] The five phases are:

1. Determine Player Order [1]

2. Auction Power Plants [1]

3. Buy Resources [1]

4. Build Houses [1]

5. Bureaucracy [1]

The Three Steps

* Step 1: The game begins with Step 1.[2] During this step, every city can only be part of the network of a single player (only one house may stand in each city).[2] The building cost for the first house is 10 Elektro.[2]

* Step 2: This step begins at the beginning of Phase 5 (Bureaucracy) after at least one player has connected a certain number of cities in their network, as determined by the number of players.[2] In Step 2, every city can be part of the networks of two players.[2] The building cost for the second house is 15 Elektro, though players may still place the first house for 10 Elektro in an empty city.[2]

* Step 3: This step begins after the Step 3 card is drawn from the power plant stack.[2] In Step 3, each city can be connected by three players.[3]

Building Houses (Phase 4)

* This phase is played in reverse player order, beginning with the last player.[4]

* Each player may choose their starting city anywhere in the contiguous playing zone.[4]

* A player may connect to any desired number of new cities during their turn, provided they can pay for them.[4]

* All subsequent cities a player adds to their network must connect to at least one city already in their network (with one of their houses).[5]

* When connecting to a new city, the player chooses the cheapest connection(s) between one of the cities in their network and the new city and pays the total of connecting costs and the cheapest building cost available (each city has spaces for three houses, valued 10, 15, and 20 Elektro) to the bank.[5]

* A player may connect to any number of new cities during their turn in this phase, as long as they pay all the building and connecting costs.[5]

* After connecting all desired cities, the player moves their house on the player order track to the same numbered space on the bottom row, and the next player follows with their turn.[5]

[1] RULEBOOK Power Grid — Rulebook · p.4 · Playing the game

[2] RULEBOOK Power Grid — Rulebook · p.7 · The 3 Steps of the Game

[3] RULEBOOK Power Grid — Rulebook · p.6 · Important rules to follow:

[4] RULEBOOK Power Grid — Rulebook · p.12 · Phase 4: Building Houses

[5] RULEBOOK Power Grid — Rulebook · p.5 · b. Pass the auction

Question closed. Friendships intact.

🔧 debug — where this ruling came from

outcome: ANSWERED — Answered
corpus profile: live,vps
answerer pin (deploy-frozen, attribution only): gemma4:26b think:false 5571076f3d70
timings: search 197 ms · ask 4825 ms · total 5024 ms
single-flight (PR-5): queued 0 ms · generation 5024 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 4, "score": 0.048916, "snippet": "The game is played over several rounds. Each round of the game has five phases. In each phase, all players take their actions in the order specified for the phase before the game continues to the next phase. The five phases are: Determine Player Order Auction Power Plants Buy Resources Build Houses ", "headingPath": "Playing the game", "sharpsignalDocId": 94}, {"page": 2, "score": 0.047643, "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": 12, "score": 0.045724, "snippet": "This phase is played in reverse player order beginning with the last player. > Each player may choose their starting city anywhere in the contiguous playing zone! > The player connects to any desired number of new cities during their turn, as long as they can pay for them. > Costs: building costs in", "headingPath": "Phase 4: Building Houses", "sharpsignalDocId": 94}, {"page": 5, "score": 0.045688, "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": 9, "score": 0.043905, "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": 8, "score": 0.031746, "snippet": "When you draw the Step 3 card from the power plant stack, Step 3 begins at the beginning of the next phase of the game!", "headingPath": "The 3 Steps of the Game", "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}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 4, "quote": null, "headingPath": "Playing the game", "sharpsignalDocId": 94}, {"page": 7, "quote": null, "headingPath": "The 3 Steps of the Game", "sharpsignalDocId": 94}, {"page": 6, "quote": null, "headingPath": "Important rules to follow:", "sharpsignalDocId": 94}, {"page": 12, "quote": null, "headingPath": "Phase 4: Building Houses", "sharpsignalDocId": 94}, {"page": 5, "quote": null, "headingPath": "b. Pass the auction", "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)
answer fence: passed — letter density 0.90142 of 1897 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row recorded: Aug 27, 2026 19:52 UTC

retrieval — what the passage search returned

what this block IS: the PASSAGE SEARCH's own results — the same search that fills this page's closest-passages list — and NOT the passages the answerer read. Answering runs its OWN retrieval: a far wider candidate pool, re-ranked down to a final handful, plus floors this search never applies — the base rulebook, surviving errata corrections, and one slot per book on a multi-book read. Each of those armed only if THIS ask sent what it needs: the boost block names the ids it forwarded, and the scope line names the books it read. A document the answer CITES that no row here names is therefore EXPECTED, not a defect: two searches, two candidate pools, two orders. The answerer's own final rows are shown in their own block below, beside these and never mixed into them.

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)	Playing the game	p.4	0.048916 (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.2	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
#3	RULEBOOK Power Grid — Rulebook (corpus doc 94)	Phase 4: Building Houses	p.12	0.045724 (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)	b. Pass the auction	p.5	0.045688 (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)	Preparation	p.9	0.043905 (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)	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
#7	RULEBOOK Power Grid — Rulebook (corpus doc 94)	The 3 Steps of the Game	p.8	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))	119
#8	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

what the answerer read — the passages it actually had in front of it

what this block IS: the passages the ANSWERING read put in front of the answerer, in the order it read them — the other half of the two reads described above, and the one that decides what the answer could possibly say. Each row names the book it came from and where in that book it sits, what it scored when the search arms were fused, which arm carried it there, and whether the re-ranker chose it or a floor guaranteed it a slot. A row here that no passage-search row names is EXPECTED: a far wider pool, re-ranked, with floors the passage search never applies.

candidate pool: the answering read scored 40 passages, out of a ceiling of 80 set gateway-side. Both figures are reported by the gateway for THIS ask — measurements of what actually happened, not constants read out of anyone's source and printed here on faith.

floors armed for this ask: the base rulebook — armed · surviving errata corrections — not armed · one slot per book on a multi-book read — not armed. Every floor is stated on every ask, armed or not, so a floor that did not apply here is never mistaken for one this app does not know about.

arms fused for this ask: vector + full-text + the doc-priority boost arm. Stated separately from the rows because an arm that ran and carried nothing is a different fact from an arm that never ran.

read at	document	heading	page	fused rank	fused RRF score	carried by	how it got its slot
#1	RULEBOOK Power Grid — Rulebook (corpus doc 94)	Playing the game	p.4	#1	0.048916 (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))	vector + full-text + the doc-priority boost arm	the re-ranker chose it
#2	RULEBOOK Power Grid — Rulebook (corpus doc 94)	Important rules to follow:	p.6	#12	0.026779 (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))	vector + full-text	the re-ranker chose it
#3	RULEBOOK Power Grid — Rulebook (corpus doc 94)	Phase 4: Building Houses	p.12	#3	0.045724 (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))	vector + full-text + the doc-priority boost arm	the re-ranker chose it
#4	RULEBOOK Power Grid — Rulebook (corpus doc 94)	Preparation	p.9	#5	0.043905 (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))	vector + full-text + the doc-priority boost arm	the re-ranker chose it
#5	RULEBOOK Power Grid — Rulebook (corpus doc 94)	The 3 Steps of the Game	p.7	#6	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))	vector + the doc-priority boost arm	the re-ranker chose it
#6	RULEBOOK Power Grid — Rulebook (corpus doc 94)	Preparation	p.2	#2	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))	vector + full-text + the doc-priority boost arm	the re-ranker chose it
#7	RULEBOOK Power Grid — Rulebook (corpus doc 94)	b. Pass the auction	p.5	#20	0.013889 (below 0.016, the low end of the measured band — a weak fuse (that band was taken on two-arm asks; only its low end, one arm's #1 vote, carries over to a 3-arm one))	vector	the re-ranker chose it
#8	RULEBOOK Power Grid — Rulebook (corpus doc 94)	Phase 1: Determine Player Order	p.4	#8	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))	vector + the doc-priority boost arm	the re-ranker chose it

chosen chunks — what the answer actually cited

#	document	heading	page	quote chars
[1]	RULEBOOK Power Grid — Rulebook (corpus doc 94)	Playing the game	p.4	no quote on the wire
[2]	RULEBOOK Power Grid — Rulebook (corpus doc 94)	The 3 Steps of the Game	p.7	no quote on the wire
[3]	RULEBOOK Power Grid — Rulebook (corpus doc 94)	Important rules to follow:	p.6	no quote on the wire
[4]	RULEBOOK Power Grid — Rulebook (corpus doc 94)	Phase 4: Building Houses	p.12	no quote on the wire
[5]	RULEBOOK Power Grid — Rulebook (corpus doc 94)	b. Pass the auction	p.5	no quote on the wire

generation — timing and the path taken

timing split: retrieval 197 ms · first delta 2078 ms · total 5024 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 197 ms · ask 4825 ms · gateway work 5024 ms · total 5024 ms
tokens in (the prompt the answerer read): 2570
tokens out (what the answerer generated): 580
tok/sec: 200.0 tok/sec — 580 output tokens in 2.900 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 43s ago)
answerer host (measured by rulesage): reachable (for 22h, checked 1s ago)
answerer node (the seat proxy's own header — this probe, not this ask): node1
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: NOT_SETUP_SHAPED — no setup-shape pattern matched this question

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.