Ruling — Fantastic Factories

You asked

How do I take my turn?

Answered counted as answered

Asked with: Fantastic Factoriesbg-216600-en-1e

The game consists of two phases: the market phase and the work phase.[1]

Market Phase

In the market phase, players take turns in order, starting with the player with the first player token and continuing clockwise.[1] On your turn, you may perform the following:

1. (Optional) Before choosing a blueprint or contractor, the active player may pay 1 metal OR 1 energy resource to discard either all the blueprints or all the contractors (but not both) in the marketplace and reveal 4 new cards from the corresponding deck.[1][2]

2. Choose one of two options:[1]

* Gain a blueprint card: Choose 1 of the 4 blueprints in the marketplace and put it in your hand for free, then refill the marketplace with the top card from the blueprint deck.[1][2]

* Hire a contractor: Choose 1 of the 4 contractors in the marketplace to hire by discarding a blueprint from your hand with the same tool symbol as the token above the contractor, then immediately discard the contractor and refill the marketplace with the top card from the contractor deck.[1]

Work Phase

During the work phase, all players take their turns simultaneously.[3]

1. Everyone picks up their dice and rolls them.[3]

2. In any order, players perform the following actions:[3][2]

* Build cards: To build a card in your hand, pay the indicated resource cost and discard another blueprint card from your hand with the same tool symbol.[3][2] There is no limit to how many times you may build in one turn as long as you can pay the costs, but you cannot build a second copy of a card with the same name unless the card text says otherwise.[3]

* Place workers: Place workers in available slots on your Headquarters player board to execute basic actions.[3] Each worker can only be used once per turn, and you cannot use the same worker for multiple actions.[4]

* Research: Place a worker on the Research floor to draw one blueprint card from the top of the blueprint deck.[3]

* Generate: Place a worker on the Generate floor to take energy resources equal to the value of the worker (the number on the die face), provided the value is 2, 3, or 4.[3]

* Mine: Place a worker on the Mine to take 1 metal resource from the supply, provided the value is 2, 3, or 4.[3]

* Activate cards: Activate cards (maximum once per card).[4][2] Cards can be activated in any order as long as activation requirements are met.[4] If a card requires workers, you must place the required workers on the card.[5]

3. After completing all actions, players must discard down to 10 cards in hand and 12 total resources (combined metal and energy).[4][2]

[1] RULEBOOK Fantastic Factories — Rulebook · p.4 · OBJECTIVE · PLAYING THE GAME · MARKET PHASE

[2] RULEBOOK Fantastic Factories — Rulebook · p.16 · PLAYER SETUP · MARKET PHASE · OR · GAME END · SCORING · WORK PHASE

[3] RULEBOOK Fantastic Factories — Rulebook · p.5 · WORK PHASE · BUILDING CARDS · BASIC ACTIONS · Research · Generate · Mine

[4] RULEBOOK Fantastic Factories — Rulebook · p.7 · ACTIVATING CARDS · ENDING THE WORK PHASE · GAME END

[5] RULEBOOK Fantastic Factories — Rulebook · p.6 · MATCHING BONUS · EXAMPLES · ACTIVATING CARDS

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 138 ms · ask 4413 ms · total 4554 ms
single-flight (PR-5): queued 0 ms · generation 4554 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 8, "score": 0.04866, "snippet": "In Solo Mode, you play against a basic simulated opponent called 'The Machine'. Rather than choosing a set of colored dice to use, you must use 4 white dice. Set up the game as normal for one player. Then deal out a number of blueprints face up to form the The Machine's starting compound. The number", "headingPath": "SOLO RULES · SETUP · YOUR TURN · THE MACHINE'S TURN", "sharpsignalDocId": 576}, {"page": 5, "score": 0.048387, "snippet": "During the work phase , all players take their turns simultaneously . However, if there are any players learning the rules for the first time, we recommend taking turns one at a time for the first round or two. The work phase begins with everyone picking up their dice and rolling them. Players then ", "headingPath": "WORK PHASE · BUILDING CARDS · BASIC ACTIONS · Research · Generate · Mine", "sharpsignalDocId": 576}, {"page": 4, "score": 0.047163, "snippet": "EAR PLANT The goal is to earn as many points as possible. Points can be earned in two ways: prestige ( ) and goods ( ). Each card in your compound is worth the prestige value printed on its top right corner. Additionally, production factories can manufacture goods that you accumulate throughout the ", "headingPath": "OBJECTIVE · PLAYING THE GAME · MARKET PHASE", "sharpsignalDocId": 576}, {"page": 9, "score": 0.031746, "snippet": "Check the green die to determine The Machine's marketplace action: , , Take the corresponding blueprint ( = left-most blueprint, = 2nd from the left, etc) from the marketplace and put it in their compound. , or : Reveal the top card of the blueprint deck and put it in their compound. Then discard al", "headingPath": "MARKET PHASE · WORK PHASE · GAME END 2 · SCORING", "sharpsignalDocId": 576}, {"page": 16, "score": 0.03125, "snippet": "Players start with 4 dice of their color, 4 random blueprints, 1 metal, and 2 energy. In turn order , each player will: (Optional) Pay 1 metal or 1 energy to discard and refill one marketplace row. 1. Gain a blueprint from the marketplace for free. 2a. Hire a contractor by discarding a card with the", "headingPath": "PLAYER SETUP · MARKET PHASE · OR · GAME END · SCORING · WORK PHASE", "sharpsignalDocId": 576}, {"page": 7, "score": 0.030303, "snippet": "Activation Order: Cards can be activated in any order as long as you can meet the activation requirements. The output is gained immediately, which can help you activate other cards or build more cards. Worker Placement: You cannot use the same worker for multiple actions. Each worker can only be use", "headingPath": "ACTIVATING CARDS · ENDING THE WORK PHASE · GAME END", "sharpsignalDocId": 576}, {"page": 11, "score": 0.029851, "snippet": "J B F Pay 1 energy to flip an unplaced die to its opposite side. Opposite sides of a die will add up to 7. For example, the opposite side of a would be a . Pay 1 energy to decrease the value of an unplaced die by 1. Fitness Center cannot be used on a . Place a die and pay energy equal to the value o", "headingPath": "Concrete Plant (2x) · Dojo (2x) · Fitness Center (3x) · Foundry (2x) · Fulfillment Center (2x) · Golem (2x) · …", "sharpsignalDocId": 576}, {"page": 11, "score": 0.029412, "snippet": "PRODUCT ION FULFILLMENT CENTER 2 1 1 2 Fulﬁllment Center (2x) Place a and pay 2 energy to gain 1 good and 1 metal. SPECIAL GOLEM Gain an extra - with a value of X this turn 1 4 Golem (2x) Pay X energy to gain an extra die of value X. Discard the extra die at the end of the round. Example: Pay 3 ener", "headingPath": "", "sharpsignalDocId": 576}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 4, "quote": null, "headingPath": "OBJECTIVE · PLAYING THE GAME · MARKET PHASE", "sharpsignalDocId": 576}, {"page": 16, "quote": null, "headingPath": "PLAYER SETUP · MARKET PHASE · OR · GAME END · SCORING · WORK PHASE", "sharpsignalDocId": 576}, {"page": 5, "quote": null, "headingPath": "WORK PHASE · BUILDING CARDS · BASIC ACTIONS · Research · Generate · Mine", "sharpsignalDocId": 576}, {"page": 7, "quote": null, "headingPath": "ACTIVATING CARDS · ENDING THE WORK PHASE · GAME END", "sharpsignalDocId": 576}, {"page": 6, "quote": null, "headingPath": "MATCHING BONUS · EXAMPLES · ACTIVATING CARDS", "sharpsignalDocId": 576}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 576 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 576 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 0.91514 of 2133 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row recorded: Oct 19, 2026 05:31 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 Fantastic Factories — Rulebook (corpus doc 576)	SOLO RULES · SETUP · YOUR TURN · THE MACHINE'S TURN	p.8	0.04866 (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 Fantastic Factories — Rulebook (corpus doc 576)	WORK PHASE · BUILDING CARDS · BASIC ACTIONS · Research · Generate · Mine	p.5	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
#3	RULEBOOK Fantastic Factories — Rulebook (corpus doc 576)	OBJECTIVE · PLAYING THE GAME · MARKET PHASE	p.4	0.047163 (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 Fantastic Factories — Rulebook (corpus doc 576)	MARKET PHASE · WORK PHASE · GAME END 2 · SCORING	p.9	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 Fantastic Factories — Rulebook (corpus doc 576)	PLAYER SETUP · MARKET PHASE · OR · GAME END · SCORING · WORK PHASE	p.16	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 Fantastic Factories — Rulebook (corpus doc 576)	ACTIVATING CARDS · ENDING THE WORK PHASE · GAME END	p.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))	300
#7	RULEBOOK Fantastic Factories — Rulebook (corpus doc 576)	Concrete Plant (2x) · Dojo (2x) · Fitness Center (3x) · Foundry (2x) · Fulfillment Center (2x) · Golem (2x) · …	p.11	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 Fantastic Factories — Rulebook (corpus doc 576)		p.11	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 20 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 Fantastic Factories — Rulebook (corpus doc 576)	WORK PHASE · BUILDING CARDS · BASIC ACTIONS · Research · Generate · Mine	p.5	#2	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 Fantastic Factories — Rulebook (corpus doc 576)	ACTIVATING CARDS · ENDING THE WORK PHASE · GAME END	p.7	#6	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
#3	RULEBOOK Fantastic Factories — Rulebook (corpus doc 576)	OBJECTIVE · PLAYING THE GAME · MARKET PHASE	p.4	#3	0.047163 (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 Fantastic Factories — Rulebook (corpus doc 576)	MATCHING BONUS · EXAMPLES · ACTIVATING CARDS	p.6	#10	0.014286 (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
#5	RULEBOOK Fantastic Factories — Rulebook (corpus doc 576)	MARKET PHASE · WORK PHASE · GAME END 2 · SCORING	p.9	#4	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))	vector + the doc-priority boost arm	the re-ranker chose it
#6	RULEBOOK Fantastic Factories — Rulebook (corpus doc 576)	PLAYER SETUP · MARKET PHASE · OR · GAME END · SCORING · WORK PHASE	p.16	#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
#7	RULEBOOK Fantastic Factories — Rulebook (corpus doc 576)		p.11	#8	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))	vector + the doc-priority boost arm	the re-ranker chose it
#8	RULEBOOK Fantastic Factories — Rulebook (corpus doc 576)	SOLO RULES · SETUP · YOUR TURN · THE MACHINE'S TURN	p.8	#1	0.04866 (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 Fantastic Factories — Rulebook (corpus doc 576)	OBJECTIVE · PLAYING THE GAME · MARKET PHASE	p.4	no quote on the wire
[2]	RULEBOOK Fantastic Factories — Rulebook (corpus doc 576)	PLAYER SETUP · MARKET PHASE · OR · GAME END · SCORING · WORK PHASE	p.16	no quote on the wire
[3]	RULEBOOK Fantastic Factories — Rulebook (corpus doc 576)	WORK PHASE · BUILDING CARDS · BASIC ACTIONS · Research · Generate · Mine	p.5	no quote on the wire
[4]	RULEBOOK Fantastic Factories — Rulebook (corpus doc 576)	ACTIVATING CARDS · ENDING THE WORK PHASE · GAME END	p.7	no quote on the wire
[5]	RULEBOOK Fantastic Factories — Rulebook (corpus doc 576)	MATCHING BONUS · EXAMPLES · ACTIVATING CARDS	p.6	no quote on the wire

generation — timing and the path taken

timing split: retrieval 138 ms · first delta 1391 ms · total 4554 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 138 ms · ask 4413 ms · gateway work 4554 ms · total 4554 ms
tokens in (the prompt the answerer read): 3548
tokens out (what the answerer generated): 621
tok/sec: 200.3 tok/sec — 621 output tokens in 3.100 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 18s ago)
answerer host (measured by rulesage): reachable (for 2h, checked 2s 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 508), 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.