Ruling — Alchemists

You asked

How do I play?

Answered counted as answered

Asked with: Alchemistsbg-161970-en-1e

The game is played in six rounds.[1] The sequence of play is as follows:

1. At the beginning of each round, players choose their play order.[1]

2. Starting with the player with the starting player marker and proceeding clockwise, each player chooses an unoccupied order space and draws the indicated cards.[1]

3. Once all players have chosen an order space and drawn their cards, players declare their actions.[2]

4. The player lowest on the order spaces declares actions first, followed by the next lowest player, and so on.[2]

5. When it is a player's turn to declare actions, they declare all their actions at once by placing action cubes on the actions they want to take.[2]

6. During the round, actions are evaluated in order, clockwise around the board.[1]

7. At the end of the round, the starting player marker is passed to the left, and the next round begins with a different starting player.[2]

[1] RULEBOOK Alchemists — Rulebook · p.8 · The Round · Choosing Play Order · Drawing Ingredients · Drawing Favor Cards · Favor Cards · Getting Nothing

[2] RULEBOOK Alchemists — Rulebook · p.8 · Paying Gold · Play Order · Declaring Actions · Example:

🔧 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 87 ms · ask 4303 ms · total 4392 ms
single-flight (PR-5): queued 0 ms · generation 4392 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 8, "score": 0.048916, "snippet": "The game is played in six rounds. At the beginning of each round, players choose their play order. Then players declare all their actions for the round. During the round, actions are evaluated in order, clockwise around the board. You start your day with a leisurely walk through the forest, looking ", "headingPath": "The Round · Choosing Play Order · Drawing Ingredients · Drawing Favor Cards · Favor Cards · Getting Nothing", "sharpsignalDocId": 325}, {"page": 8, "score": 0.046032, "snippet": "Sometimes you don't even have time to make breakfast. Instead, you buy fresh rolls from the baker and eat them on your way through town. To choose this space, you must pay 1 gold piece. If you don't have the gold, you can't choose this space. On this space you draw no cards, but you are guaranteed t", "headingPath": "Paying Gold · Play Order · Declaring Actions · Example:", "sharpsignalDocId": 325}, {"page": 3, "score": 0.045002, "snippet": "To be a successful alchemist, you need to keep an orderly notebook. The results triangle is for recording the results of your experiment. Take a token and put it at the intersection of mushroom and toad. The deduction grid is for recording what your experiment tells you. Your experiment eliminates 4", "headingPath": "Deduction · The Gamemaster Board", "sharpsignalDocId": 325}, {"page": 4, "score": 0.044796, "snippet": "4 SetupSetup Master or Master or Apprentice? Apprentice? You can play Alchemists either as masters or apprentices. For your first game, we recommend you play the apprentice variant. A few of the rules are simpler, and the academic conferences are more forgiving. Even so, it offers the full range of ", "headingPath": "", "sharpsignalDocId": 325}, {"page": 7, "score": 0.04359, "snippet": "Arrange them as shown. Each player puts one flask on the 10 space to mark initial reputation. Used only in the master variant. For the apprentice variant, leave these in the box. At the start of the game, launch the app, select the master or apprentice variant, and tap the button. The app will rando", "headingPath": "grants · reputation markers · alchemical tokens · Initializing the Card Reader · Starting Player Token", "sharpsignalDocId": 325}, {"page": 10, "score": 0.043494, "snippet": "If multiple players drink a potion, they will all have their order markers on the green space at the bottom. Those who put their markers there first will play ahead of those who put their markers there later. If the starting player marker is passed to a player who is paralyzed, the paralyzed player ", "headingPath": "Other Fun Things That Can Happen To You When You Are Paralyzed", "sharpsignalDocId": 325}, {"page": 9, "score": 0.03125, "snippet": "On each action space, players take their actions in order, beginning with the player on the highest occupied row. When you take your action, remove your cube. (Or remove both cubes if the action requires 2 cubes.) Once everyone on the action space has taken their first action, players with two actio", "headingPath": "Resolving Action Spaces · Declining Your Action · Actions Available in the First Round", "sharpsignalDocId": 325}, {"page": 16, "score": 0.030303, "snippet": "If any ingredient cards are left in the ingredients row, remove them. Deal 5 new ingredients to the row. If the deck runs out (during setup or at any other time) shuffle the discard pile to make a new deck. Move all the order markers off the order spaces. (Except for any that were put on the paralys", "headingPath": "Setup For Next Round", "sharpsignalDocId": 325}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 8, "quote": null, "headingPath": "The Round · Choosing Play Order · Drawing Ingredients · Drawing Favor Cards · Favor Cards · Getting Nothing", "sharpsignalDocId": 325}, {"page": 8, "quote": null, "headingPath": "Paying Gold · Play Order · Declaring Actions · Example:", "sharpsignalDocId": 325}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 325 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 325 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 0.92256 of 749 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row retained until: Nov 15, 2026 08:32

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 Alchemists — Rulebook (corpus doc 325)	The Round · Choosing Play Order · Drawing Ingredients · Drawing Favor Cards · Favor Cards · Getting Nothing	p.8	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 Alchemists — Rulebook (corpus doc 325)	Paying Gold · Play Order · Declaring Actions · Example:	p.8	0.046032 (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 Alchemists — Rulebook (corpus doc 325)	Deduction · The Gamemaster Board	p.3	0.045002 (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 Alchemists — Rulebook (corpus doc 325)		p.4	0.044796 (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 Alchemists — Rulebook (corpus doc 325)	grants · reputation markers · alchemical tokens · Initializing the Card Reader · Starting Player Token	p.7	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
#6	RULEBOOK Alchemists — Rulebook (corpus doc 325)	Other Fun Things That Can Happen To You When You Are Paralyzed	p.10	0.043494 (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 Alchemists — Rulebook (corpus doc 325)	Resolving Action Spaces · Declining Your Action · Actions Available in the First Round	p.9	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
#8	RULEBOOK Alchemists — Rulebook (corpus doc 325)	Setup For Next Round	p.16	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

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 56 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 Alchemists — Rulebook (corpus doc 325)	The Round · Choosing Play Order · Drawing Ingredients · Drawing Favor Cards · Favor Cards · Getting Nothing	p.8	#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 Alchemists — Rulebook (corpus doc 325)	Paying Gold · Play Order · Declaring Actions · Example:	p.8	#2	0.046032 (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 Alchemists — Rulebook (corpus doc 325)	Web-Based Card Reader · adventurer tiles · conference tiles · Master or Apprentice? · Two, Three, or Four Players?	p.4	#9	0.029324 (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
#4	RULEBOOK Alchemists — Rulebook (corpus doc 325)		p.6	#15	0.026161 (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 Alchemists — Rulebook (corpus doc 325)	Barmaid · Custodian · Herbalist · Merchant	p.20	#12	0.027888 (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
#6	RULEBOOK Alchemists — Rulebook (corpus doc 325)	Publish Theory · Publishing a New Theory	p.13	#17	0.025645 (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 Alchemists — Rulebook (corpus doc 325)	Transmute Ingredient	p.9	#11	0.028169 (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
#8	RULEBOOK Alchemists — Rulebook (corpus doc 325)		p.4	#4	0.044796 (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 Alchemists — Rulebook (corpus doc 325)	The Round · Choosing Play Order · Drawing Ingredients · Drawing Favor Cards · Favor Cards · Getting Nothing	p.8	no quote on the wire
[2]	RULEBOOK Alchemists — Rulebook (corpus doc 325)	Paying Gold · Play Order · Declaring Actions · Example:	p.8	no quote on the wire

generation — timing and the path taken

timing split: retrieval 87 ms · first delta 3334 ms · total 4392 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 87 ms · ask 4303 ms · gateway work 4392 ms · total 4392 ms
tokens in (the prompt the answerer read): 4009
tokens out (what the answerer generated): 207
tok/sec: 204.3 tok/sec — 207 output tokens in 1.013 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 0s 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: 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 253), 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.