You asked
How do I set up the game?
Answered counted as answeredAsked with: Lords of Waterdeepbg-110327-en-1e
1. Lay out the game board [1]. 2. Each player chooses a color and takes a number of that color's Agents based on the number of players (4 agents for 2 players; 3 agents for 3 players; 2 agents for 4 or 5 players) [2][1]. 3. Each player places 1 more Agent of their color near the Round 5 space of the rounds track [2][1]. 4. Each player places their score marker on the scoring track at the position labeled '0' [2][1]. 5. Place the Adventurer cubes and Gold within easy reach of all players [1]. 6. Place the Building stack, Quest deck, and Intrigue deck in the appropriate spaces on the gameboard [1]. 7. Draw 3 Building tiles and place them face up in each of the 3 spaces in Builder's Hall [1]. 8. Each player takes a player mat [1]. 9. Deal 1 Lord card face down to each player [1]. 10. Deal 2 Quest cards face up to each player [1]. 11. Place 1 face-up Quest card in each of the 4 spaces of Cliffwatch Inn [1]. 12. Shuffle the Intrigue cards and deal 2 cards face down to each player [3]. 13. Place 3 VP tokens on each space of the rounds track [1]. 14. Identify the starting player (the player who has most recently been to another city) and give them the First Player marker [3][1]. 15. Distribute starting Gold: the starting player gets 4 Gold, and each subsequent player receives 1 more Gold than the player to their right until all players have received starting Gold [3][1].
🔧 debug — where this ruling came from
- outcome
- ANSWERED — Answered
- corpus profile
- live
- answerer pin (deploy-frozen, attribution only)
- gemma4:26b think:false 5571076f3d70
- timings
- search 272 ms · ask 9105 ms · total 1585770 ms
- single-flight (PR-5)
- queued 1576383 ms · generation 9387 ms
- retrieval refs (raw)
- [{"page": 13, "score": 0.048916, "snippet": "Lay out the game board. Each player chooses a color and takes a number of that color's Agents that depends on the number of players. | Number of Players | Agents per Player | | 2 | 4 | | 3 | 3 | | 4 | 2 | | 5 | 2 | Each player also places 1 more Agent of his or her color near the Round 5 space of th", "headingPath": "seTup · seQuenCe of play · Rules RefeRenCe · aCTions in a TuRn", "sharpsignalDocId": 127}, {"page": 5, "score": 0.048131, "snippet": "8 The Lords of Waterdeep game is played in rounds . During each round, players take turns in which they assign their Agents to various tasks. The game ends after 8 rounds have passed. The player with the most VP at the end of the eighth round is the winner. The rounds track on the game board starts ", "headingPath": "sTaRT play · seQuenCe of play · sTaRT of Round · aCTions in a TuRn", "sharpsignalDocId": 127}, {"page": 3, "score": 0.047643, "snippet": "4 The Lords of Waterdeep ™ game is played in eight rounds . The player with the most Victory Points at the end of the final round is the winner. Before you can start playing, you'll need to spend a bit of time setting up the game. The game board represents the various Wards of the city of Waterdeep.", "headingPath": "Game ComponenTs · How To win · seTup · Game boaRd · aGenTs · sCoRe maRkeRs", "sharpsignalDocId": 127}, {"page": 4, "score": 0.031746, "snippet": "Intrigue cards let you secretly manipulate others to advance your ends. But be careful-your fellow Lords of Waterdeep are also skilled in intrigue! Shuffle the Intrigue cards and deal 2 cards face down to each player. Keep these cards hidden from your opponents. See 'Play Intrigue Card' on page 9 fo", "headingPath": "inTRiGue CaRds · sTaRT play", "sharpsignalDocId": 127}, {"page": 5, "score": 0.030769, "snippet": "If you have any Agents in your pool, you assign 1 of them. To assign an Agent, place it on any unoccupied action space of a Building, whether a basic Building or one that has been put into play. You cannot place an Agent on an action space that contains another Agent (yours or another player's) or o", "headingPath": "assiGn aGenT · buildeR's Hall", "sharpsignalDocId": 127}, {"page": 3, "score": 0.030303, "snippet": "Each player takes a player mat that matches his or her Agents' color. This helps keep track of various game resources. Agent Pool: Here is where you keep Agents that you have not yet assigned (see 'Assign Agent' on page 8). At the end of the round, all of your assigned Agents return to your pool. Ta", "headingPath": "playeR maTs", "sharpsignalDocId": 127}, {"page": 13, "score": 0.029851, "snippet": "Assign Agent: Place 1 Agent from your pool on an unoccupied action space of a Building. You cannot skip your turn if you have Agents available to assign. If you have no Agents left to assign, you cannot take a turn. Play proceeds to the next player until all Agents have been assigned. Reassign Agent", "headingPath": "2. Complete Quest · final sCoRinG", "sharpsignalDocId": 127}, {"page": 4, "score": 0.029412, "snippet": "Each Building, whether printed on the game board or a tile in Builder's Hall, contains the same kinds of information. See 'Assign Agent' on page 8 for more information. Name: You can look up more detailed information about the Building by finding its name in Appendix 1: Buildings beginning on page 1", "headingPath": "ReadinG a buildinG · CaRds · loRd CaRds · QuesT CaRds", "sharpsignalDocId": 127}]
- citations (raw)
- [{"page": 13, "quote": null, "headingPath": "seTup · seQuenCe of play · Rules RefeRenCe · aCTions in a TuRn", "sharpsignalDocId": 127}, {"page": 3, "quote": null, "headingPath": "Game ComponenTs · How To win · seTup · Game boaRd · aGenTs · sCoRe maRkeRs", "sharpsignalDocId": 127}, {"page": 4, "quote": null, "headingPath": "inTRiGue CaRds · sTaRT play", "sharpsignalDocId": 127}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 127 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 127 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)
- debug row retained until
- Nov 6, 2026 14:36
retrieval — what the search arm returned
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 Lords of Waterdeep — Rulebook (corpus doc 127) | seTup · seQuenCe of play · Rules RefeRenCe · aCTions in a TuRn | p.13 | 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 Lords of Waterdeep — Rulebook (corpus doc 127) | sTaRT play · seQuenCe of play · sTaRT of Round · aCTions in a TuRn | p.5 | 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 Lords of Waterdeep — Rulebook (corpus doc 127) | Game ComponenTs · How To win · seTup · Game boaRd · aGenTs · sCoRe maRkeRs | p.3 | 0.047643 (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 Lords of Waterdeep — Rulebook (corpus doc 127) | inTRiGue CaRds · sTaRT play | 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 |
| #5 | RULEBOOK Lords of Waterdeep — Rulebook (corpus doc 127) | assiGn aGenT · buildeR's Hall | p.5 | 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 |
| #6 | RULEBOOK Lords of Waterdeep — Rulebook (corpus doc 127) | playeR maTs | p.3 | 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 Lords of Waterdeep — Rulebook (corpus doc 127) | 2. Complete Quest · final sCoRinG | p.13 | 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 Lords of Waterdeep — Rulebook (corpus doc 127) | ReadinG a buildinG · CaRds · loRd CaRds · QuesT CaRds | p.4 | 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 |
chosen chunks — what the answer actually cited
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.
| # | document | heading | page | quote chars |
|---|---|---|---|---|
| [1] | RULEBOOK Lords of Waterdeep — Rulebook (corpus doc 127) | seTup · seQuenCe of play · Rules RefeRenCe · aCTions in a TuRn | p.13 | no quote on the wire |
| [2] | RULEBOOK Lords of Waterdeep — Rulebook (corpus doc 127) | Game ComponenTs · How To win · seTup · Game boaRd · aGenTs · sCoRe maRkeRs | p.3 | no quote on the wire |
| [3] | RULEBOOK Lords of Waterdeep — Rulebook (corpus doc 127) | inTRiGue CaRds · sTaRT play | p.4 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 272 ms · first delta 6736 ms · total 1585770 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 1576383 ms · retrieval 272 ms · ask 9105 ms · gateway work 9387 ms · total 1585770 ms
- tokens in (the prompt the answerer read)
- 3572
- tokens out (what the answerer generated)
- 386
- tok/sec
- 148.1 tok/sec — 386 output tokens in 2.606 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 56s 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
- SERVED — setup-shaped and this game's approved setup checklist is offered above
- pattern that matched
- SETUP — "setup" / "set up"
- matched words (in the normalized question)
-
set up
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 49), 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.