(Tentative)
| Definition | Functional Requirements | Syntax | Semantics |
Definition
PA-Prompt Plan (PGM-PAP)
- Is produced by the Personality Alignment (PAL) AIM.
- Encapsulates a structured semantic scaffold for refining, reframing, or regenerating enriched responses.
- Aligns output with the A-User’s expressive stance and evolving interaction context.
Functional Requirements
PA-Prompt Plan conveys the following main information elements:
| Function | Description |
| Expressive Feedback Transmission | Encodes expressive modulation cues from Personality Alignment, including tone, style, pacing, and persona traits. Preserves alignment decisions made in Personality State and PA-Input. |
| Narrative Refinement Directive | Includes a directive for BKN to refine, reframe, or regenerate its prior output. Supports goals such as elaboration, simplification, contrast, emotional shift, or rhetorical reorientation. |
| Persona Continuity | Includes persona framing (e.g., “curious guide”) to guide BKN’s narrative voice. Optionally includes behavioural constraints or expressive boundaries. |
| Content Anchoring | References the BKN fragment being refined or extended. Optionally includes a summary or excerpt of the original enriched response. |
| Interaction Context | Includes the current focus of interaction (ItemID, ItemType, and optional description). Preserves continuity with Personality State and PA-Input. |
| User State Context | Includes interpreted user state (engagement, affective tone, disposition) to guide BKN’s expressive modulation. Optionally includes override flags for tone or pacing enforcement. |
Syntax
https://schemas.mpai.community/PGM1/V1.0/data/PAPromptPlan.json
Semantics
| Label | Description |
| Header | PA-Prompt Plan Header |
| ├─ Standard-APP | The characters “PGM-PPP-V” |
| ├─ Version | Major version – 1 or 2 characters |
| ├─ Dot-separator | The character “.” separating version components |
| └─ Subversion | Minor version – 1 or 2 characters |
| PAPromptPlanID | Unique identifier for this PA-Prompt Plan instance |
| MInstanceID | Identifier of the metaverse instance |
| MEnvironmentID | Identifier of the metaverse environment |
| ExpressiveFeedback | Modulated expressive cues from Personality Alignment |
| ├─ Tone | Desired tone for BKN refinement (empathetic, assertive, etc.) |
| ├─ Style | Desired stylistic preference (concise, elaborate, etc.) |
| ├─ Pacing | Suggested pacing for BKN response (slow, steady, fast) |
| └─ PersonaTrait | Persona framing for BKN narrative voice (curious guide, etc.) |
| NarrativeDirective | Instruction for BKN refinement or regeneration |
| ├─ Goal | Narrative goal (clarify, deepen, contrast, etc.) |
| ├─ Mode | Rhetorical mode (explanatory, reflective, persuasive, etc.) |
| └─ OverrideFlags | Optional flags enforcing expressive constraints |
| ContentAnchor | Reference to BKN fragment being refined |
| ├─ BKFragmentID | ID of the BKN fragment |
| └─ Excerpt | Optional excerpt of the original enriched response |
| InteractionFocus | Current focus of interaction |
| ├─ ItemID | Identifier of the focused Item |
| ├─ ItemType | Semantic category (from ItemTypeTaxonomy.json) |
| └─ Description | Natural language description of the Item |
| UserState | User state context for expressive modulation |
| ├─ EngagementLevel | User’s cognitive engagement level (low, moderate, high) |
| ├─ AffectiveTone | Emotional tone inferred from user response (neutral, positive, etc.) |
| └─ Disposition | Inferred user disposition or attitude |
| Trace | Provenance metadata for PA Prompt Plan |
| ├─ PersonalityStateID | Reference to the originating Personality State |
| ├─ PAInputID | Reference to the originating PA-Input |
| ├─ BKFragmentID | ID of the BKN fragment being refined |
| └─ Timestamp | Time of PAD-To-BKN creation (see Time.json) |
