You asked
How do I set up the game?
Answered counted as answeredAsked with: Mansions of Madness: Second Editionbg-205059-en-1e
Before playing each game, perform the following steps in order: 1. Separate the Investigator cards from all other cards [1]. 2. Separate all other cards into decks by card type [1]. 3. Shuffle the Damage and Horror decks individually and place them facedown in the central play area [1]. 4. Organize the cards in the Common Item, Unique Item, Spell, and Condition decks alphabetically and place them faceup within reach of all players [1]. 5. Gather all map tiles and organize them by tile size [1]. 6. Make sure that each monster figure has a matching token slotted into its base [1]. 7. Separate all non-monster tokens into pools by token type [1]. 8. Run the Mansions of Madness app [1]. 9. From the main menu, select "More" and then "My Collection" to ensure all desired products and expansions are enabled [1]. 10. From the main menu, select 'New Game' [1]. 11. As a group, players decide which story to play and input their selection in the app [1]. (Note: Players also select a scenario during setup that determines winning objectives [2]). 12. Each player chooses an investigator, taking the card and figure for that investigator, and inputs the selected investigators in the app [1]. (If playing with a single player, that player chooses two investigators and controls both [1]). 13. As instructed by the app, investigators as a group gain specific Common Items, Spells, or other possessions, which may be distributed among them however they decide [1]. 14. Read aloud the scenario's prologue as shown by the app [3]. 15. Place the starting map tile or tiles and the investigators' figures as instructed by the app [3]. 16. Place features, Search tokens, and Explore tokens on the game board as instructed by the app [3]. 17. Perform any other steps as instructed by the app [3].
🔧 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 259 ms · ask 11692 ms · total 1423016 ms
- single-flight (PR-5)
- queued 1411055 ms · generation 11961 ms
- retrieval refs (raw)
- [{"page": 3, "score": 0.048172, "snippet": "Perform the following steps to complete setup: Read aloud the scenario's prologue as shown by the app. The story's prologue may provide hints at what is to come. Place the starting map tile or tiles and the investigators' figures as instructed by the app. Place features, Search tokens, and Explore t", "headingPath": "9. Read pRologUe and Reveal enTRance", "sharpsignalDocId": 277}, {"page": 2, "score": 0.047643, "snippet": "This document is intended as a reference for all rules queries. Unlike the Learn to Play booklet, this reference does not teach players how to play the game. Players should first read the Learn to Play booklet in its entirety, then use this reference as needed when playing the game. This Rules Refer", "headingPath": "Using This RefeRence · Table of conTenTs · seTUp.............................................. p age 3 · glossaRy ....................................... p age 4 · app scReen anaTomy ............... p age 20 · monsTeR figURe RefeRence .... p age 22 · …", "sharpsignalDocId": 277}, {"page": 3, "score": 0.047183, "snippet": "Before playing each game, perform the following steps in order. Separate the Investigator cards from all other cards. They will be used later during setup. Then separate all other cards into decks by card type. ^ Shuffle the Damage and Horror decks individually and place them facedown in the central", "headingPath": "conflicTs · 1. cReaTe caRd decks · 2. oRganize map Tiles · 3. oRganize monsTeRs · 4. cReaTe Token pools · 5. UpdaTe collecTion · …", "sharpsignalDocId": 277}, {"page": 20, "score": 0.046898, "snippet": "During the game, players will primarily interact with the in-game user interface. Map: The majority of the screen is the map. As players explore the scenario location and reveal more of the map, those tiles and the tokens on them will be displayed in the central area of the screen. Only those tokens", "headingPath": "in-game inTeRface", "sharpsignalDocId": 277}, {"page": 16, "score": 0.04598, "snippet": "Players can save the progress of the current scenario and quit to the main menu. They can resume playing during another session. ^ A player can save and quit by selecting the option from the in-game menu in the app. ^ If players intend to resume the game at a later time, they should record their pos", "headingPath": "save & QUiT · seaRch acTion · seaRch Token · secReT passage · seT fiRe acTion", "sharpsignalDocId": 277}, {"page": 19, "score": 0.045475, "snippet": "During setup, players select a scenario that determines what the investigators need to do to win the game. However, this objective is hidden information. ^ During the game, the investigators must unravel the mystery and discover their ultimate goal. The investigators can do so by listening carefully", "headingPath": "winning & losing", "sharpsignalDocId": 277}, {"page": 14, "score": 0.043301, "snippet": "During the game, investigators can view their objective by accessing the in-game menu in the app. ^ The objective indicates what the investigator should be doing and/or how they can win the game. ^ The app will track only the basic objectives that investigators must accomplish to finish the scenario", "headingPath": "objecTive · oUTdooR · peRson · pick Up · place · possessions", "sharpsignalDocId": 277}, {"page": 22, "score": 0.030303, "snippet": "To assemble the monster figures, insert each figure's pegs into the appropriate base. Attach the Star Spawns to the large bases, the Hunting Horrors and Riots to the medium bases, and all other figures to the small bases. After attaching each figure to its base, insert each monster token into its ma", "headingPath": "monsTeR figURe seTUp", "sharpsignalDocId": 277}]
- citations (raw)
- [{"page": 3, "quote": null, "headingPath": "conflicTs · 1. cReaTe caRd decks · 2. oRganize map Tiles · 3. oRganize monsTeRs · 4. cReaTe Token pools · 5. UpdaTe collecTion · …", "sharpsignalDocId": 277}, {"page": 19, "quote": null, "headingPath": "winning & losing", "sharpsignalDocId": 277}, {"page": 3, "quote": null, "headingPath": "9. Read pRologUe and Reveal enTRance", "sharpsignalDocId": 277}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 277 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 277 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 14:33
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 Mansions of Madness: Second Edition — Rulebook (corpus doc 277) | 9. Read pRologUe and Reveal enTRance | p.3 | 0.048172 (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 Mansions of Madness: Second Edition — Rulebook (corpus doc 277) | Using This RefeRence · Table of conTenTs · seTUp.............................................. p age 3 · glossaRy ....................................... p age 4 · app scReen anaTomy ............... p age 20 · monsTeR figURe RefeRence .... p age 22 · … | p.2 | 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 |
| #3 | RULEBOOK Mansions of Madness: Second Edition — Rulebook (corpus doc 277) | conflicTs · 1. cReaTe caRd decks · 2. oRganize map Tiles · 3. oRganize monsTeRs · 4. cReaTe Token pools · 5. UpdaTe collecTion · … | p.3 | 0.047183 (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 Mansions of Madness: Second Edition — Rulebook (corpus doc 277) | in-game inTeRface | p.20 | 0.046898 (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 Mansions of Madness: Second Edition — Rulebook (corpus doc 277) | save & QUiT · seaRch acTion · seaRch Token · secReT passage · seT fiRe acTion | p.16 | 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 |
| #6 | RULEBOOK Mansions of Madness: Second Edition — Rulebook (corpus doc 277) | winning & losing | p.19 | 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 Mansions of Madness: Second Edition — Rulebook (corpus doc 277) | objecTive · oUTdooR · peRson · pick Up · place · possessions | p.14 | 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 Mansions of Madness: Second Edition — Rulebook (corpus doc 277) | monsTeR figURe seTUp | p.22 | 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 |
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 Mansions of Madness: Second Edition — Rulebook (corpus doc 277) | conflicTs · 1. cReaTe caRd decks · 2. oRganize map Tiles · 3. oRganize monsTeRs · 4. cReaTe Token pools · 5. UpdaTe collecTion · … | p.3 | no quote on the wire |
| [2] | RULEBOOK Mansions of Madness: Second Edition — Rulebook (corpus doc 277) | winning & losing | p.19 | no quote on the wire |
| [3] | RULEBOOK Mansions of Madness: Second Edition — Rulebook (corpus doc 277) | 9. Read pRologUe and Reveal enTRance | p.3 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 259 ms · first delta 8808 ms · total 1423016 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 1411055 ms · retrieval 259 ms · ask 11692 ms · gateway work 11961 ms · total 1423016 ms
- tokens in (the prompt the answerer read)
- 3243
- tokens out (what the answerer generated)
- 423
- tok/sec
- 136.5 tok/sec — 423 output tokens in 3.099 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 32s 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
- NO_APPROVED_CHECKLIST — setup-shaped, but no approved setup checklist exists for this game
- 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 205), 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.