(Tentative)
| Definition | Functional Requirements | Syntax | Semantics |
Definition
DA-Prompt Plan (PGM-DPP)
- Is produced by the Domain Access (DAC) AIM.
- Encapsulates a structured semantic scaffold integrating User intent, resolved referents, spatial context, and expressive framing.
- Supports the generation of a DA Prompt that is contextually rich and linguistically aligned for submission to Basic Knowledge (BKN).
Functional Requirements
DA-Prompt Plan conveys the following main information elements:
| Function | Description |
| Intent Embedding | Includes the current user intent motivating the knowledge query. Supports alignment with User State and PC-Prompt Plan. |
| Referent Structuring | Includes resolved entities with semantic roles and linguistic cues. Supports referential clarity and disambiguation. |
| Spatial Context Integration | Includes relevant spatial primitives and scene descriptors. Supports grounding of the query in physical or conceptual space. |
| Goal Framing | Encodes the communicative goal of the prompt (e.g., explain, compare, locate). Supports BKN response shaping and semantic continuity. |
| Expressive Modulation | Includes tone, style, and pacing cues for linguistic alignment. Supports expressive coherence across modules. |
| Constraint Injection | Includes semantic or interaction constraints relevant to the query. Supports filtering or prioritisation in BKN response logic. |
| Traceability | Includes origin metadata and timestamp for audit and replay. |
Syntax
https://schemas.mpai.community/PGM1/V1.0/data/DAPromptPlan.json
Semantics
| Label | Description |
| Header | DA-Prompt Plan Header |
| – Standard-DPP | The characters “PGP-DPP-V” |
| – Version | Major version – 1 or 2 characters |
| – Dot-separator | The character “.” separating version components |
| – Subversion | Minor version – 1 or 2 characters |
| PromptPlanID | Unique identifier for this DA-Prompt Plan instance |
| Intent | User intent motivating the knowledge query |
| Referents | Resolved entities with semantic roles and cues |
| ├─ ReferentID | Identifier of the resolved entity |
| ├─ ReferentType | Type of entity: object, zone, concept, actor |
| └─ LinguisticCue | Suggested phrasing (e.g., “to your left”, “nearby”) |
| SpatialContext | Spatial relations and scene-level descriptors |
| ├─ SpatialPrimitives | Relation + SubjectID + ObjectID + optional LinguisticCue |
| └─ SceneContextTags | High-level descriptors of spatial situation (e.g., “crowded”, “behind avatar”) |
| PromptGoal | Communicative goal of the prompt |
| ├─ GoalType | Type of goal: explain, compare, locate, summarise |
| └─ TargetEntity | Entity the prompt is centered on |
| ExpressiveFrame | Modulation cues for tone, style, and pacing |
| ├─ Tone | Expressive stance: empathetic, assertive, playful, formal, neutral |
| ├─ Style | Linguistic style: concise, elaborate, technical, casual |
| └─ Pacing | Delivery speed: slow, steady, fast |
| Constraints | Semantic or interaction constraints |
| ├─ ConstraintType | Type of constraint (e.g., relevance, visibility, priority) |
| └─ ConstraintValue | Entity or concept involved |
| Trace | Provenance metadata |
| ├─ Origin | Module or subsystem that generated the prompt plan |
| └─ Timestamp | Time of creation (conforming to Time.json) |
