A human example
A player returns to a room after hearing its introduction.
What the caller supplies
The game removes completed cues and supplies current facts, timing and remaining recordings.
What happens next
Jev recommends a cue or silence. The game rejects stale advice and owns playback.
Illustrative example, not a recorded result.
Potential value: medium
Could improve the timing and variety of authored reactions without generating new dialogue.
Evidence confidence: low
The optional game integration exists, but no independent playthrough study establishes a better experience.
The rating describes support for this claim. It is separate from Jev's returned probability. How we assign ratings.
Evidence, including disagreement
- Define ambiguity before evaluating a workflow. reference. Specify what uncertain and mixed cases should do.
The next test
20 scripted playthrough paths plus human review, covering return visits, waiting, interruptions and scene changes.
Compare against
- Current deterministic director
- Optional Jev advice
Measure
- Repeated lines
- Interruptions
- Stale recommendations rejected
- Player preference
- Added delays
Decision after the test
Keep narration optional. Require no repeat or stale-playback regression and a clear preference in reviewed playthroughs.
The report will retain inputs, question versions, every attempt and failure examples. We will update the confidence rating after reviewing the result.
Use a related Engine recipe
Recipes are implementation starting points. Their presence does not mean the protocol above has passed.