Ruling — Tawantinsuyu: The Inca Empire

← Tawantinsuyu: The Inca Empire

You asked

How do I play?

Answered counted as answered

Asked with: Tawantinsuyu: The Inca Empirebg-306481-en-1e

Before taking your first turn, you must place your High Priest on any space on the Coricancha tile.[1]

On your turn, you must choose one of the following two options:

1. Place a Worker: Discard 1 God card or 1 gold to place a Worker from your supply on the game board.[1]

2. Perform 2 different secondary actions, in any order: Moving the High Priest, Praying, Training, or Recruiting.[1]

Secondary Actions:

* Moving the High Priest: Moving the High Priest clockwise 1 or 2 steps and activate or gain 1.[2]

* Praying: Take 2 God cards from the offer or the top of the deck.[2]

* Training: Draw 2 Army cards, keep one, and discard the other.[2]

* Recruiting: Take 1 Worker from Nomads for free, then refill Nomads from the bag.[2]

Additional Turn Rules:

* As a free action at any time during your turn, you may discard any number of Army cards from your hand to gain the resources depicted on them.[1]

* At the end of your turn, you may recruit more Workers, but you can never end your turn with more than 2 in your supply.[1]

* At the end of your turn, replenish the Building Market if you constructed any Buildings, ensuring there are exactly four face-up Buildings (two of each type).[1]

* If the Village is empty at the end of your turn, a Festival is triggered.[1]

[1] RULEBOOK Tawantinsuyu: The Inca Empire — Rulebook · p.8 · One turn of play

[2] RULEBOOK Tawantinsuyu: The Inca Empire — Rulebook · p.4

That's the page. Back to the table.

🔧 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 98 ms · ask 4723 ms · total 4823 ms
single-flight (PR-5): queued 0 ms · generation 4823 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 6, "score": 0.048387, "snippet": "Lay out the main game board in the center of the play area. Place all resources next to the board to form a general supply. Give each player all their Step markers. Place their Scoring marker on the 10 space of the score track and their Temple marker on the bottommost space of the Temple track. Rota", "headingPath": "WORKERS", "sharpsignalDocId": 1094}, {"page": 14, "score": 0.046402, "snippet": "Immediately upon initiating Conquest, you must select a Worker from either end of the Village queue and place it in the Casualties of War area. If the Village is empty, select from the Nomads instead; then, draw a Worker from the bag, and place it in the emptied Nomad space. All players may now (in ", "headingPath": "Conquest", "sharpsignalDocId": 1094}, {"page": 22, "score": 0.046239, "snippet": "As much as it can afford (costs as usual). As much as it can afford As much as it can afford (costs as usual). For your first game (for an easier experience), leave all Personality tokens in the box, and leave the Gold icon visible. (costs as usual). Plays all Army cards in hand for free. Chooses sp", "headingPath": "Gaining Workers", "sharpsignalDocId": 1094}, {"page": 8, "score": 0.04612, "snippet": "Special First Turn Rule : Before taking your first turn of the game, start by placing your High Priest on the Coricancha tile on any of the spaces (even one already occupied by one or more High Priests belonging to other players). This placement only serves to determine the starting position of your", "headingPath": "One turn of play", "sharpsignalDocId": 1094}, {"page": 7, "score": 0.045235, "snippet": "Separate Buildings by type: Production and Passive . Shuffle the Production and Passive Buildings separately, and create two face-down stacks. Then, reveal 2 Buildings of each type next to each of the Building stacks. This becomes the Building Market. Shuffle the Army cards, and place them in a face", "headingPath": "WORKERS", "sharpsignalDocId": 1094}, {"page": 17, "score": 0.04359, "snippet": "After the first and second Festival, players draw God cards from the deck (during this phase players are not allowed to draw cards from the offer) as follows (in order from the player with the fewest VP to the player with the most VP): In a 4-player game , the player with the fewest VP draws 2 cards", "headingPath": "FESTIVAL CARD DRAW", "sharpsignalDocId": 1094}, {"page": 25, "score": 0.030303, "snippet": "If Axomamma has no Worker to place, see the No Worker section on page 26. If Axomamma does not trigger a High Priest action and it has at least one Worker, it will place a Worker on the board and perform an action. If it has multiple Workers to pick from, it places its 'oldest' (or if this is its fi", "headingPath": "Axomamma Board Action", "sharpsignalDocId": 1094}, {"page": 14, "score": 0.029412, "snippet": "Instead of placing a Worker, you may choose two different secondary actions and perform them in any order. These actions often allow other players -in turn order -to perform some version of the action you choose. You may move your High Priest 1 or 2 steps (sections) clockwise around the Coricancha a", "headingPath": "Performing 2 secondary actions · HIGH PRIEST SECONDARY ACTION · Rejuvenate", "sharpsignalDocId": 1094}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 8, "quote": null, "headingPath": "One turn of play", "sharpsignalDocId": 1094}, {"page": 4, "quote": null, "headingPath": "", "sharpsignalDocId": 1094}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 1094 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1094 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 0.88962 of 1060 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row recorded: Sep 5, 2026 15:37 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 Tawantinsuyu: The Inca Empire — Rulebook (corpus doc 1094)	WORKERS	p.6	0.048387 (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 Tawantinsuyu: The Inca Empire — Rulebook (corpus doc 1094)	Conquest	p.14	0.046402 (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 Tawantinsuyu: The Inca Empire — Rulebook (corpus doc 1094)	Gaining Workers	p.22	0.046239 (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 Tawantinsuyu: The Inca Empire — Rulebook (corpus doc 1094)	One turn of play	p.8	0.04612 (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 Tawantinsuyu: The Inca Empire — Rulebook (corpus doc 1094)	WORKERS	p.7	0.045235 (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 Tawantinsuyu: The Inca Empire — Rulebook (corpus doc 1094)	FESTIVAL CARD DRAW	p.17	0.04359 (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 Tawantinsuyu: The Inca Empire — Rulebook (corpus doc 1094)	Axomamma Board Action	p.25	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 Tawantinsuyu: The Inca Empire — Rulebook (corpus doc 1094)	Performing 2 secondary actions · HIGH PRIEST SECONDARY ACTION · Rejuvenate	p.14	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

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 49 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 Tawantinsuyu: The Inca Empire — Rulebook (corpus doc 1094)	WORKERS	p.6	#1	0.048387 (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 Tawantinsuyu: The Inca Empire — Rulebook (corpus doc 1094)	Conquest	p.14	#2	0.046402 (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
#3	RULEBOOK Tawantinsuyu: The Inca Empire — Rulebook (corpus doc 1094)	One turn of play	p.8	#4	0.04612 (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 Tawantinsuyu: The Inca Empire — Rulebook (corpus doc 1094)	Conquest · PRAYING SECONDARY ACTION · TRAINING SECONDARY ACTION	p.16	#14	0.02632 (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
#5	RULEBOOK Tawantinsuyu: The Inca Empire — Rulebook (corpus doc 1094)	WORKERS	p.7	#5	0.045235 (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
#6	RULEBOOK Tawantinsuyu: The Inca Empire — Rulebook (corpus doc 1094)		p.22	#15	0.026151 (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
#7	RULEBOOK Tawantinsuyu: The Inca Empire — Rulebook (corpus doc 1094)	Gaining Workers	p.22	#3	0.046239 (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
#8	RULEBOOK Tawantinsuyu: The Inca Empire — Rulebook (corpus doc 1094)		p.4	#10	0.028531 (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

chosen chunks — what the answer actually cited

#	document	heading	page	quote chars
[1]	RULEBOOK Tawantinsuyu: The Inca Empire — Rulebook (corpus doc 1094)	One turn of play	p.8	no quote on the wire
[2]	RULEBOOK Tawantinsuyu: The Inca Empire — Rulebook (corpus doc 1094)		p.4	no quote on the wire

generation — timing and the path taken

timing split: retrieval 98 ms · first delta 2995 ms · total 4823 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 98 ms · ask 4723 ms · gateway work 4823 ms · total 4823 ms
tokens in (the prompt the answerer read): 3994
tokens out (what the answerer generated): 342
tok/sec: 198.0 tok/sec — 342 output tokens in 1.727 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 13s ago)
answerer host (measured by rulesage): reachable (for 22h, checked 3s 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 1024), 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.