Ruling — Agent Avenue

You asked

How do I play?

Answered counted as answered

Asked with: Agent Avenuebg-422732-en-1e

To play, follow these steps in order:

1. Play: Play 2 cards from your hand in the center of the table, 1 face up and 1 face down.[1] These 2 cards must have different card names, unless all cards in your hand have the same name.[2][1] Optional: Before you play a card, you may choose a card from your hand and discard it face down in front of you to draw a new one; this can be done multiple times on the same turn, but only 2 times in the entire game.[3] (Note: One source states this can be done up to 4 times in the entire game [4]). After playing both cards, draw from the agent deck until you have 4 cards in hand.[1]

2. Recruit: The opponent must recruit 1 of the 2 agent cards you have played by choosing 1 card and putting it face up in front of them.[4] You must then recruit the other agent card by putting it face up in front of you.[4] The players of the opposing team agree on which card to recruit: either the face-up card or the face-down card.[3] If you recruit your 4th, 5th, or 6th agent of the same name, you treat it as your 3rd.[2] Then, both players move their meeple on the board.[5] To move, look at the agent just recruited: if you have only 1 of that name in play, look at its 1st icon on the top; if you have 2, look at its 2nd icon in the center; if you have 3 or more, look at its 3rd icon on the bottom.[5] Move your meeple forward (clockwise) by the indicated number of spaces, or backward (counterclockwise) if the number is negative.[5] If the number is zero or there is no number, do not move.[5] Your opponent does the same with their meeple.[5]

3. End: After both meeples have moved, check whether any player fulfills a condition to win or lose the game.[5] You can win the game only during the End step.[2] A player wins if they catch their opponent's meeple, which occurs if their meeple's position reaches or exceeds the position of the opponent's meeple.[5] If no one wins or loses and the agent deck is empty and an opponent has no cards in hand, the game ends, and the team closer to catching their opponent's meeple wins.[3] If the condition is not met, your turn ends and your opponent's turn begins.[5]

[1] RULEBOOK Agent Avenue — Rulebook · p.5 · WINNING THE GAME · CARDS IN HAND · GAME TURN · STEP 1 : PLAY

[2] RULEBOOK Agent Avenue — Rulebook · p.9 · REMINDERS & CLARIFICATIONS

[3] RULEBOOK Agent Avenue — Rulebook · p.15 · GAME TURN STEP 1 : PLAY · STEP 2 : RECRUIT · STEP 3 : END

[4] RULEBOOK Agent Avenue — Rulebook · p.6 · STEP 1 : PLAY · STEP 2 : RECRUIT

[5] RULEBOOK Agent Avenue — Rulebook · p.7 · STEP 2 : RECRUIT · STEP 3 : END

🔧 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 110 ms · ask 4319 ms · total 4431 ms
single-flight (PR-5): queued 0 ms · generation 4431 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 14, "score": 0.048916, "snippet": "Divide all players into 2 teams. Teammates sit next to each other, facing the opposing team. At 4 players, both teams have 2 players. At 3 players, one team has 2 players while the other player plays on their own. Deal each player 4 agent cards in hand. You may not look at your teammate's cards. You", "headingPath": "GAME SETUP · GAME TURN STEP 1 : PLAY", "sharpsignalDocId": 549}, {"page": 5, "score": 0.046875, "snippet": "You are attempting to unmask the secret identity of your opponent by catching their meeple on the board before they catch yours. To achieve this, you will recruit agents in your neighborhood. Your progress is represented by your meeple's position on the board, relative to the position of your oppone", "headingPath": "WINNING THE GAME · CARDS IN HAND · GAME TURN · STEP 1 : PLAY", "sharpsignalDocId": 549}, {"page": 7, "score": 0.046343, "snippet": "Then both players move their meeple on the board. To move your meeple, look at the agent you have just recruited. Check how many agent cards with that same name you have in play, including the one you have just recruited. If you have only 1 , look at its 1st icon on the top. If you have 2 , look at ", "headingPath": "STEP 2 : RECRUIT · STEP 3 : END", "sharpsignalDocId": 549}, {"page": 9, "score": 0.046244, "snippet": "During the Play step, the 2 cards you play from your hand (1 face up and 1 face down) must have different card names. In the rare case that all the cards in your hand have the same card name, it is allowed to play 2 identical cards. If the agent deck is empty, you can't discard an agent card from yo", "headingPath": "REMINDERS & CLARIFICATIONS", "sharpsignalDocId": 549}, {"page": 6, "score": 0.045688, "snippet": "Optional: Before you play cards, you may choose a card from your hand and discard it face down in front of you to draw a new one. You can do this multiple times on the same turn, but only 4 times in the entire game. The opponent must recruit 1 of the 2 agent cards you have played. To do so, they cho", "headingPath": "STEP 1 : PLAY · STEP 2 : RECRUIT", "sharpsignalDocId": 549}, {"page": 15, "score": 0.045475, "snippet": "Remember to draw cards from the agent deck until you have 4 cards in hand. Optional: Before you play a card (no matter if your teammate has already played a card or not), you may choose a card from your hand and discard it face down in front of you to draw a new one. You can do this multiple times o", "headingPath": "GAME TURN STEP 1 : PLAY · STEP 2 : RECRUIT · STEP 3 : END", "sharpsignalDocId": 549}, {"page": 10, "score": 0.043301, "snippet": "With the advanced mode, you can play a more varied and challenging game. The players will get access to new assets and events that will provide unique benefits and tactics. The advanced mode introduces an additional deck of cards, called the black market cards . They help you win the game with their", "headingPath": "Advanced Mode · GAME SETUP", "sharpsignalDocId": 549}, {"page": 4, "score": 0.031746, "snippet": "If you are new to the game, it is recommended to use only the rules of the simple mode . Once you are familiar with the game, you can then read the rules of the advanced mode and the team variant . 1 Place the board in the center of the table, with the side for the simple mode face up. 2 Each player", "headingPath": "Components · GAME SETUP", "sharpsignalDocId": 549}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 5, "quote": null, "headingPath": "WINNING THE GAME · CARDS IN HAND · GAME TURN · STEP 1 : PLAY", "sharpsignalDocId": 549}, {"page": 9, "quote": null, "headingPath": "REMINDERS & CLARIFICATIONS", "sharpsignalDocId": 549}, {"page": 15, "quote": null, "headingPath": "GAME TURN STEP 1 : PLAY · STEP 2 : RECRUIT · STEP 3 : END", "sharpsignalDocId": 549}, {"page": 6, "quote": null, "headingPath": "STEP 1 : PLAY · STEP 2 : RECRUIT", "sharpsignalDocId": 549}, {"page": 7, "quote": null, "headingPath": "STEP 2 : RECRUIT · STEP 3 : END", "sharpsignalDocId": 549}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 549 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 549 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 0.91364 of 1737 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row retained until: Nov 16, 2026 17:52

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 Agent Avenue — Rulebook (corpus doc 549)	GAME SETUP · GAME TURN STEP 1 : PLAY	p.14	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 Agent Avenue — Rulebook (corpus doc 549)	WINNING THE GAME · CARDS IN HAND · GAME TURN · STEP 1 : PLAY	p.5	0.046875 (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 Agent Avenue — Rulebook (corpus doc 549)	STEP 2 : RECRUIT · STEP 3 : END	p.7	0.046343 (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 Agent Avenue — Rulebook (corpus doc 549)	REMINDERS & CLARIFICATIONS	p.9	0.046244 (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 Agent Avenue — Rulebook (corpus doc 549)	STEP 1 : PLAY · STEP 2 : RECRUIT	p.6	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
#6	RULEBOOK Agent Avenue — Rulebook (corpus doc 549)	GAME TURN STEP 1 : PLAY · STEP 2 : RECRUIT · STEP 3 : END	p.15	0.045475 (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 Agent Avenue — Rulebook (corpus doc 549)	Advanced Mode · GAME SETUP	p.10	0.043301 (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 Agent Avenue — Rulebook (corpus doc 549)	Components · GAME SETUP	p.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))	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 15 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 Agent Avenue — Rulebook (corpus doc 549)	STEP 1 : PLAY · STEP 2 : RECRUIT	p.6	#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))	vector + full-text + the doc-priority boost arm	the re-ranker chose it
#2	RULEBOOK Agent Avenue — Rulebook (corpus doc 549)	GAME TURN STEP 1 : PLAY · STEP 2 : RECRUIT · STEP 3 : END	p.15	#6	0.045475 (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 Agent Avenue — Rulebook (corpus doc 549)	REMINDERS & CLARIFICATIONS	p.9	#4	0.046244 (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 Agent Avenue — Rulebook (corpus doc 549)	Advanced Mode · GAME SETUP	p.10	#7	0.043301 (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 Agent Avenue — Rulebook (corpus doc 549)	STEP 2 : RECRUIT · STEP 3 : END	p.7	#3	0.046343 (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 Agent Avenue — Rulebook (corpus doc 549)	Components · GAME SETUP	p.4	#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))	vector + the doc-priority boost arm	the re-ranker chose it
#7	RULEBOOK Agent Avenue — Rulebook (corpus doc 549)	WINNING THE GAME · CARDS IN HAND · GAME TURN · STEP 1 : PLAY	p.5	#2	0.046875 (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 Agent Avenue — Rulebook (corpus doc 549)	GAME SETUP · GAME TURN STEP 1 : PLAY	p.14	#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

chosen chunks — what the answer actually cited

#	document	heading	page	quote chars
[1]	RULEBOOK Agent Avenue — Rulebook (corpus doc 549)	WINNING THE GAME · CARDS IN HAND · GAME TURN · STEP 1 : PLAY	p.5	no quote on the wire
[2]	RULEBOOK Agent Avenue — Rulebook (corpus doc 549)	REMINDERS & CLARIFICATIONS	p.9	no quote on the wire
[3]	RULEBOOK Agent Avenue — Rulebook (corpus doc 549)	GAME TURN STEP 1 : PLAY · STEP 2 : RECRUIT · STEP 3 : END	p.15	no quote on the wire
[4]	RULEBOOK Agent Avenue — Rulebook (corpus doc 549)	STEP 1 : PLAY · STEP 2 : RECRUIT	p.6	no quote on the wire
[5]	RULEBOOK Agent Avenue — Rulebook (corpus doc 549)	STEP 2 : RECRUIT · STEP 3 : END	p.7	no quote on the wire

generation — timing and the path taken

timing split: retrieval 110 ms · first delta 1683 ms · total 4431 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 110 ms · ask 4319 ms · gateway work 4431 ms · total 4431 ms
tokens in (the prompt the answerer read): 1996
tokens out (what the answerer generated): 564
tok/sec: 207.8 tok/sec — 564 output tokens in 2.714 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 50s 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 481), 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.