Ruling — Llamaland

You asked

How do I play?

Answered counted as answered

Asked with: Llamalandbg-330038-en-1e

The game is played as follows:

1. The start player takes the first turn, and play moves clockwise around the table.[1]

2. On your turn, you may use any number of character cards in your collection to perform additional actions before and after placing your land tile.[2]

3. You must place 1 land tile of your choice from the top of its draw pile to either extend or build your estate.[1]

* To extend: Place the chosen tile next to your start board or other land tiles extending your estate, ensuring at least one space is orthogonally adjacent to an existing space in your estate.[1]

* To build: Place the chosen tile on top of your start board or other previously placed land tiles, ensuring the spaces line up with the spaces below, there are no gaps or llamas below the tile, and the tile is not placed completely on top of a tile of the same shape.[3]

* You may rotate or flip the new tile as you wish.[1][3]

* If building, you gain benefits for each icon covered by the tile you just placed (Corn, Cacao, Potato, Coin, or Huts) in an order of your choice.[3]

4. After extending or building, you may choose to feed 1 llama (if you have 10 or more crop tokens in your collection, you must feed a llama).[4]

* To feed a llama: Return 4 corn, 4 cacao, or 4 potato tokens from your collection to the supply and take the corresponding llama card with the highest value from the center of the play area, placing it face up in your collection.[4]

* You may return 2 coins from your collection to the supply to substitute for any crop token any number of times.[4]

* After feeding, you must take a llama figure from the supply and place it in your estate on an empty space without an icon.[4]

5. After extending, you may also place one of your markers on an empty space on an objective card of your choice, or move one of your markers from an objective card to another empty space on the same or a different objective card.[1] You can have at most one marker on an objective card.[1]

6. The game ends when the end of the game is triggered: if there is only 1 type of llama cards or only 4 total land tiles remaining in the center of the play area.[5] Play continues until all players have had an equal number of turns.[5] If the trigger occurs on the turn of the player to the right of the start player, the game ends immediately.[5]

7. Scoring: Total the victory points from these four sources:

* Each llama card is worth its listed number of victory points.[5]

* Each remaining crop in your collection is worth 1 victory point.[5]

* Every 2 remaining coins in your collection are worth 1 victory point, rounded down.[5]

* Each marker on an objective card scores as indicated on its space, provided you meet the condition depicted at the top of that card.[5]

8. The player with the highest total wins; in case of a tie, the player who scored the most victory points from llama cards wins.[5]

[1] RULEBOOK Llamaland — Rulebook · p.3 · Course of Play · PLACING A LAND TILE · Extending · Placing a Marker

[2] RULEBOOK Llamaland — Rulebook · p.6 · Using Character Cards · Example of a turn:

[3] RULEBOOK Llamaland — Rulebook · p.4 · Building · Collecting Benefits

[4] RULEBOOK Llamaland — Rulebook · p.5 · Using Foundation Tiles · FEEDING A LLAMA

[5] RULEBOOK Llamaland — Rulebook · p.7 · Game End and Scoring · BEGINNER'S VARIANT · EXPERT VARIANT · LLAMA VARIANT

The book has spoken.

🔧 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 91 ms · ask 4479 ms · total 4572 ms
single-flight (PR-5): queued 0 ms · generation 4572 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 3, "score": 0.04918, "snippet": "The start player takes the first turn and then play moves clockwise around the table, until the end of the game is triggered (see 'Game End and Scoring' on page 7) . During the game, you will be placing land tiles on and next to your start board. This is called your estate . You will also be gatheri", "headingPath": "Course of Play · PLACING A LAND TILE · Extending · Placing a Marker", "sharpsignalDocId": 1302}, {"page": 7, "score": 0.048131, "snippet": "At the end of a turn, if there is only 1 type of llama cards or only 4 total land tiles remaining in the center of the play area, the end of the game is triggered. Play continues until you all have had an equal number of turns. If the end is triggered on the turn of the player to the right of the st", "headingPath": "Game End and Scoring · BEGINNER'S VARIANT · EXPERT VARIANT · LLAMA VARIANT", "sharpsignalDocId": 1302}, {"page": 2, "score": 0.047371, "snippet": "Shuffle all the land tiles and place them in 5 stacks according to shape in the center of the play area. Place all the crop tokens , coins , and llama figures in separate supply piles nearby. Sort the llama cards by type (depicted at the top of each card and indicated by color) . For each type, rand", "headingPath": "SETUP", "sharpsignalDocId": 1302}, {"page": 5, "score": 0.04598, "snippet": "Before building, you may choose to place any number of your remaining foundation tiles in your estate, to make placing your land tile easier. Foundations may be placed in any position on the table or any level, as long as the land tile being placed completely covers all played foundations. Foundatio", "headingPath": "Using Foundation Tiles · FEEDING A LLAMA", "sharpsignalDocId": 1302}, {"page": 1, "score": 0.03125, "snippet": "by Phil Walker-Harding |2-4 players | Ages 10+ | 30-60 minutes Being a farmer is not exactly easy with all the hills and mountains around. Yet, growing potatoes, corn, and cacao is what you love; and the landscape is wild, stunningly beautiful, and … full of llamas?! Fitting your fields in giddy hei", "headingPath": "Object of the Game · Components", "sharpsignalDocId": 1302}, {"page": 6, "score": 0.030769, "snippet": "On your turn, you may use any number of character cards in your collection to perform additional actions. You may do so before and after placing your land tile. Each character card may only be used once per turn -turn a card sideways to show it has been used. You may have multiple copies of the same", "headingPath": "Using Character Cards · Example of a turn:", "sharpsignalDocId": 1302}, {"page": 4, "score": 0.030303, "snippet": "Place the chosen tile on top of your start board or other previously placed land tiles, according to the following rules. You may rotate or flip the new tile as you wish. The spaces of the tile must line up with the spaces below it. There may be no gaps (i.e., areas where there is no tile) or llamas", "headingPath": "Building · Collecting Benefits", "sharpsignalDocId": 1302}, {"page": 7, "score": 0.029412, "snippet": "Designer: Phil Walker-Harding Editing: Ralph Bienert, Hanno Girke Rule book: Phil Walker-Harding, Grzegorz Kobiela Illustrations: Klemens Franz Graphic design: atelier198 For rules questions, suggestions, or criticism, please contact us at: rules@lookout-games.de For missing pieces or damaged parts,", "headingPath": "Credits", "sharpsignalDocId": 1302}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 3, "quote": null, "headingPath": "Course of Play · PLACING A LAND TILE · Extending · Placing a Marker", "sharpsignalDocId": 1302}, {"page": 6, "quote": null, "headingPath": "Using Character Cards · Example of a turn:", "sharpsignalDocId": 1302}, {"page": 4, "quote": null, "headingPath": "Building · Collecting Benefits", "sharpsignalDocId": 1302}, {"page": 5, "quote": null, "headingPath": "Using Foundation Tiles · FEEDING A LLAMA", "sharpsignalDocId": 1302}, {"page": 7, "quote": null, "headingPath": "Game End and Scoring · BEGINNER'S VARIANT · EXPERT VARIANT · LLAMA VARIANT", "sharpsignalDocId": 1302}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 1302 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1302 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 0.93106 of 2350 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row recorded: Sep 5, 2026 15:31 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 Llamaland — Rulebook (corpus doc 1302)	Course of Play · PLACING A LAND TILE · Extending · Placing a Marker	p.3	0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1)	300
#2	RULEBOOK Llamaland — Rulebook (corpus doc 1302)	Game End and Scoring · BEGINNER'S VARIANT · EXPERT VARIANT · LLAMA VARIANT	p.7	0.048131 (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 Llamaland — Rulebook (corpus doc 1302)	SETUP	p.2	0.047371 (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 Llamaland — Rulebook (corpus doc 1302)	Using Foundation Tiles · FEEDING A LLAMA	p.5	0.04598 (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 Llamaland — Rulebook (corpus doc 1302)	Object of the Game · Components	p.1	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
#6	RULEBOOK Llamaland — Rulebook (corpus doc 1302)	Using Character Cards · Example of a turn:	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
#7	RULEBOOK Llamaland — Rulebook (corpus doc 1302)	Building · Collecting Benefits	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
#8	RULEBOOK Llamaland — Rulebook (corpus doc 1302)	Credits	p.7	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 9 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 Llamaland — Rulebook (corpus doc 1302)	Course of Play · PLACING A LAND TILE · Extending · Placing a Marker	p.3	#1	0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1)	vector + full-text + the doc-priority boost arm	the re-ranker chose it
#2	RULEBOOK Llamaland — Rulebook (corpus doc 1302)	Game End and Scoring · BEGINNER'S VARIANT · EXPERT VARIANT · LLAMA VARIANT	p.7	#2	0.048131 (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 Llamaland — Rulebook (corpus doc 1302)	Using Foundation Tiles · FEEDING A LLAMA	p.5	#4	0.04598 (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 Llamaland — Rulebook (corpus doc 1302)	Building · Collecting Benefits	p.4	#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))	vector + the doc-priority boost arm	the re-ranker chose it
#5	RULEBOOK Llamaland — Rulebook (corpus doc 1302)	Objective Card Index	p.8	#9	0.014493 (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
#6	RULEBOOK Llamaland — Rulebook (corpus doc 1302)	Using Character Cards · Example of a turn:	p.6	#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))	vector + the doc-priority boost arm	the re-ranker chose it
#7	RULEBOOK Llamaland — Rulebook (corpus doc 1302)	Object of the Game · Components	p.1	#5	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))	vector + the doc-priority boost arm	the re-ranker chose it
#8	RULEBOOK Llamaland — Rulebook (corpus doc 1302)	SETUP	p.2	#3	0.047371 (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

chosen chunks — what the answer actually cited

#	document	heading	page	quote chars
[1]	RULEBOOK Llamaland — Rulebook (corpus doc 1302)	Course of Play · PLACING A LAND TILE · Extending · Placing a Marker	p.3	no quote on the wire
[2]	RULEBOOK Llamaland — Rulebook (corpus doc 1302)	Using Character Cards · Example of a turn:	p.6	no quote on the wire
[3]	RULEBOOK Llamaland — Rulebook (corpus doc 1302)	Building · Collecting Benefits	p.4	no quote on the wire
[4]	RULEBOOK Llamaland — Rulebook (corpus doc 1302)	Using Foundation Tiles · FEEDING A LLAMA	p.5	no quote on the wire
[5]	RULEBOOK Llamaland — Rulebook (corpus doc 1302)	Game End and Scoring · BEGINNER'S VARIANT · EXPERT VARIANT · LLAMA VARIANT	p.7	no quote on the wire

generation — timing and the path taken

timing split: retrieval 91 ms · first delta 1021 ms · total 4572 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 91 ms · ask 4479 ms · gateway work 4572 ms · total 4572 ms
tokens in (the prompt the answerer read): 3522
tokens out (what the answerer generated): 695
tok/sec: 199.0 tok/sec — 695 output tokens in 3.493 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 1232), 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.