You asked
how do i start?
Answered counted as answeredTo start, each player must decide which character they are going to play [1]. Before beginning Scenario 1, you may also place a "Roadside Ambush" sticker on the city map board [1]. Once the game is set up properly, gameplay begins in rounds where players select ability cards to determine the initiative order [2].
Strategy guides → — community tips, kept separate from rulings
🔧 debug — where this ruling came from
- outcome
- ANSWERED — Answered
- corpus profile
- live
- answerer pin (deploy-frozen, attribution only)
- gemma4:12b think:false 4eb23ef187e2
- timings
- search 120 ms · ask 3348 ms · total 3476 ms
- single-flight (PR-5)
- queued 0 ms · generation 3476 ms
- retrieval refs (raw)
- [{"page": 6, "score": 0.031754, "snippet": "Now that the game has been set up properly, we can start playing! Gameplay within a scenario is broken up into a series of rounds. In each round, all players will select which ability cards they would like to play. The chosen cards will determine the \"initiative order\", which is the sequence in whic", "headingPath": "Playing the Game", "sharpsignalDocId": 61}, {"page": 14, "score": 0.030886, "snippet": "And so, we move on to Scenario 2! First, start by turning to Scenario 2 in the Scenario Book. Then, the setup will be largely the same as the setup in Scenario 1 (see p. 4), with the following changes:", "headingPath": "Scenario 2 Rules", "sharpsignalDocId": 61}, {"page": 7, "score": 0.030769, "snippet": "Once all players have selected their cards, flip over each character's cards to reveal their initiative. Determine initiative order by comparing the initiative value of each character's initiative card and the initiative of the monsters (this will always be 50 for Scenario 1). Then, arrange the init", "headingPath": "Ordering of Initiative", "sharpsignalDocId": 61}, {"page": 30, "score": 0.029907, "snippet": "There are a few other rules we weren't able to introduce yet that you will need as you go deeper into the campaign. These are outlined below, but also note that the Rules Glossary contains a comprehensive detailing of all the rules in the game. If you ever have a question about anything, you will fi", "headingPath": "Final Rules", "sharpsignalDocId": 61}, {"page": 13, "score": 0.029631, "snippet": "Now that you have recorded everything important pertaining to the outcome of Scenario 1, you can continue reading the next page to start playing Scenario 2, or you can put everything back in the box to continue the campaign another time. The most important thing is to put all the materials currently", "headingPath": "Saving", "sharpsignalDocId": 61}, {"page": 15, "score": 0.029514, "snippet": "With the scenario now set up, we just have to go over a few more rules introduced by your new ability cards and the new monster ability deck, and then we can start playing.", "headingPath": "New Aetion Mechanies", "sharpsignalDocId": 61}, {"page": 24, "score": 0.02886, "snippet": "Starting now, each time you successfully complete a scenario, you must encounter a city event. Before doing this for the first time, however, retrieve the \"events\" deck from the game box and shuffle the cards. Then, draw the top card of the deck and read the introductory text ①on the front. This wil", "headingPath": "New City Interaction: Events", "sharpsignalDocId": 61}, {"page": 4, "score": 0.027778, "snippet": "Using these character materials and other components, we will now set up Scenario 1. Each player should place their character mat ①, player reference , six level \"A\" ability cards 3 , attack modifier deck (the deck of smaller cards) , and hit point dial in front of them. The red side of the dial sho", "headingPath": "Play Area Setup", "sharpsignalDocId": 61}]
- citations (raw)
- [{"page": 3, "quote": null, "headingPath": "Scenario 1 Rules", "sharpsignalDocId": 61}, {"page": 6, "quote": null, "headingPath": "Playing the Game", "sharpsignalDocId": 61}]
- boost provenance — errata + base rulebook (E2/E3)
- gate not evaluated for this ruling (boost, supersedence, and wrench all off at ask time), and the base-rulebook arm went unrecorded for the same reason — the wrench that would have stored it was off; rulesage.errata.boost-enabled=false, rulesage.errata.supersedence-enabled=false
- 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
- Oct 9, 2026 02:34
retrieval — what the search arm returned
score = the fused retrieval score (reciprocal-rank fusion over the search arms) — NOT a cosine similarity. How many arms fused this ruling was NOT RECORDED (it predates the boost trail, ran on the path that stored none, or stored one that could not be read), and the ceiling depends on that count (ceiling = arms/(k+1) at k=60): 2 arms top out at 0.03279; 3 arms top out at 0.04918. So a score above 0.03279 here is not an anomaly: it is arithmetic proof a boost arm voted, and the measured band 0.016–0.033 (taken on two-arm asks) is what does not apply. 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 Gloomhaven: Jaws of the Lion — Rulebook (corpus doc 61) | Playing the Game | p.6 | 0.031754 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #2 | RULEBOOK Gloomhaven: Jaws of the Lion — Rulebook (corpus doc 61) | Scenario 2 Rules | p.14 | 0.030886 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 201 |
| #3 | RULEBOOK Gloomhaven: Jaws of the Lion — Rulebook (corpus doc 61) | Ordering of Initiative | p.7 | 0.030769 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #4 | RULEBOOK Gloomhaven: Jaws of the Lion — Rulebook (corpus doc 61) | Final Rules | p.30 | 0.029907 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #5 | RULEBOOK Gloomhaven: Jaws of the Lion — Rulebook (corpus doc 61) | Saving | p.13 | 0.029631 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #6 | RULEBOOK Gloomhaven: Jaws of the Lion — Rulebook (corpus doc 61) | New Aetion Mechanies | p.15 | 0.029514 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 172 |
| #7 | RULEBOOK Gloomhaven: Jaws of the Lion — Rulebook (corpus doc 61) | New City Interaction: Events | p.24 | 0.02886 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #8 | RULEBOOK Gloomhaven: Jaws of the Lion — Rulebook (corpus doc 61) | Play Area Setup | p.4 | 0.027778 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 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 Gloomhaven: Jaws of the Lion — Rulebook (corpus doc 61) | Scenario 1 Rules | p.3 | no quote on the wire |
| [2] | RULEBOOK Gloomhaven: Jaws of the Lion — Rulebook (corpus doc 61) | Playing the Game | p.6 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 120 ms · first delta n/a · total 3476 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 120 ms · ask 3348 ms · gateway work 3476 ms · total 3476 ms
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 33s ago)
- stream path
- not recorded — this ruling predates the stream-path column (V41)
- 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
- HOW_DO_I_START — "how do I start"
- matched words (in the normalized question)
-
how do i start
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 9), 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.