Go to PGM-AUA V1.0 AI Modules

Function Ref. Model I/O Data SubAIMs JSON MData Profiles Ref. Software Conformance Performance

1. Function

The Prompt Creation (PGM‑PRC) AIM assembles, organises, and submits a structured representation of the current understanding of the Context by the A‑User with respect to the Space and the User to Basic Knowledge for deliberation. Its role is to bind together perceptual, state, contextual, and historical information into a coherent representation suitable for deliberative processing by Basic Knowledge.

Prompt Creation operates through two interfaces:

  • Operational Interface – receives Context Descriptors, A‑User Storage references, and Interaction History under instruction from A‑User Control, and assembles PC Prompt.
  • Semantic Interface (MCP) – maintains a session‑oriented, multi‑turn interaction with Basic Knowledge over the BKN‑PRC Interaction, responding to requests to refine, restructure, or clarify elements of PC Prompt.

Prompt Creation may be activated by:

  • An instruction from A‑User Control to construct or update PC Prompt.
  • A BKN‑PRC Request from Basic Knowledge to refine, restructure, or clarify elements of an existing PC Prompt.
  • Changes in Context Descriptors, User State, or Interaction History that require PC Prompt to be updated.

Prompt Creation acts as the sole Context Representation Provider. It is the only AIM responsible for assembling Context Descriptors, User Entity State, A‑User Storage references, and Interaction History into a coherent situation representation for deliberation by Basic Knowledge.

Prompt Creation:

  1. Operates on the Context Descriptors produced by Context Enhancement, the PRC Directive received from A‑User Control, the PRC Interaction History Response retrieved from A‑User Storage, and the BKN‑PRC Request received from Basic Knowledge via MCP.
  2. Produces the PC Prompt submitted to Basic Knowledge for deliberation, the PRC‑BKN Response sent to Basic Knowledge via MCP, and the PRC Status reported to A‑User Control.
  3. ??May issue clarifications to Context Description because of request received fro BK<

2. Reference Model

Figure 1 depicts the Reference Model of the Prompt Creation (PGM‑PRC) AIM.

Figure 1 – Reference Model of the Prompt Creation (PGM‑PRC) AIM

3. Input/Output Data

Table 1 specifies the Input and Output Data of the Prompt Creation (PGM‑PRC) AIM.

Table 1 – Input/Output Data of the Prompt Creation (PGM‑PRC) AIM

Input Description
Context Descriptors Enhanced Audio and Visual Scene Descriptors and audio‑visual alignment information produced by Context Enhancement.
PRC Interaction History Response Interaction History associated with the current session, retrieved from A‑User Storage.
PRC Directive Instructions from A‑User Control specifying assembly scope, AUS references to retrieve, and AUS content to store.
BKN‑PRC Request Message from Basic Knowledge via MCP to refine, restructure, or clarify elements of PC Prompt.
Output Description
PC Prompt Structured situation representation submitted to Basic Knowledge for deliberation.
PRC‑BKN Response Message to Basic Knowledge via MCP providing refined or clarified PC Prompt elements.
PRC Interaction History Request Request to A‑User Storage for additional Interaction History.
PRC Status Status information describing the execution and outcome of PRC processing, reported to A‑User Control.

4. SubAIMs (Informative)

This section is informative. The decomposition into SubAIMs described below illustrates one conformant architecture for producing the normative outputs of PGM‑PRC. Implementations may adopt alternative internal structures provided they satisfy the conformance requirements of Section 8.

4.1 Reference Model

Figure 2 depicts the Reference Model of the Prompt Creation (PGM‑PRC) Composite AIM.

Figure 2 – Reference Model of the Prompt Creation (PGM‑PRC) Composite AIM

 

4.2 Operation

The Prompt Creation operation receives Context Descriptors, Interaction History, and control signals, and progressively transforms them into a structured PC Prompt through a sequence of specialised SubAIMs.

The Prompt Token Analyser parses and tokenises the Context Descriptors and Interaction History into a structured Token Stream suitable for subsequent analysis.

The Intent Inference SubAIM infers the communicative intent and goal of the A‑User from the Token Stream and prior interaction history, producing Intent Candidates.

The User State Adaptation SubAIM adapts the tone and phrasing of the PC Prompt to reflect the current User Entity State, producing a Tone Profile and Phrasing Hints.

The Referent Resolution SubAIM resolves references to spatial entities, objects, users, and prior interaction elements within the Token Stream, producing Resolved Referents and a Resolution Confidence score.

The Scene Context Tagging SubAIM tags scene elements with contextual labels derived from the Intent Candidates and Tone Profile, producing Scene Context Tags and Timing Hints.

The Goal Constraint Derivation SubAIM derives goal and constraint structures from intent inference and phrasing context for inclusion in PC Prompt, producing Goal Constraints and Prompt Triggers.

The Spatial Primitive Extraction SubAIM extracts spatial primitives and geometric relationships from Resolved Referents to ground spatial reasoning in PC Prompt.

The PC‑Prompt Planner SubAIM plans the structure and ordering of the assembled PC Prompt from all intermediate outputs, for optimal deliberative processing by Basic Knowledge.

The PRC Prompt Formatter SubAIM formats the planned PC Prompt into the structured form expected by Basic Knowledge and packages it for MCP submission.

4.3 Functions of SubAIMs

Table 2 specifies the functions of the SubAIMs of the Prompt Creation (PGM‑PRC) Composite AIM.

Table 2 – Functions of the SubAIMs of the Prompt Creation (PGM‑PRC) Composite AIM

Name Function
Prompt Token Analyser Parses and tokenises Context Descriptors and Interaction History into structured prompt tokens.
Intent Inference Infers the communicative intent and goal of the A‑User from the Token Stream and prior interaction history.
User State Adaptation Adapts tone and phrasing of PC Prompt to reflect the current User Entity State.
Referent Resolution Resolves references to spatial entities, objects, users, and prior PC Prompt elements.
Scene Context Tagging Tags scene elements with contextual labels derived from Intent Candidates and Tone Profile.
Goal Constraint Derivation Derives goal and constraint structures from intent inference and phrasing context for inclusion in PC Prompt.
Spatial Primitive Extraction Extracts spatial primitives and geometric relationships from Resolved Referents to ground spatial reasoning.
PC‑Prompt Planner Plans the structure and ordering of the assembled PC Prompt for optimal deliberative processing by Basic Knowledge.
PRC Prompt Formatter Formats and packages PC Prompt into the structured form expected by Basic Knowledge for MCP submission.

4.4 Input/Output Data of SubAIMs

Table 3 lists the Input and Output Data of the SubAIMs of the Prompt Creation (PGM‑PRC) Composite AIM.

Table 3 – Input/Output Data of the SubAIMs of the Prompt Creation (PGM‑PRC) Composite AIM

Name Input Data Output Data
Prompt Token Analyser Context Descriptors
PRC Directive
PRC IH Response
BKN‑PRC Request
Token Stream
PRC Status
PRC IH Request
PRC‑BKN Response
Intent Inference Token Stream
PRC Directive
PRC IH Response
BKN‑PRC Request
Intent Candidates
PRC Status
PRC IH Request
PRC‑BKN Response
User State Adaptation Intent Candidates
PRC Directive
PRC IH Response
BKN‑PRC Request
Tone Profile
Phrasing Hints
PRC Status
Referent Resolution Token Stream
PRC Directive
PRC IH Response
BKN‑PRC Request
Resolved Referents
Resolution Confidence
PRC Status
PRC IH Request
PRC‑BKN Response
Scene Context Tagging Intent Candidates
Tone Profile
BKN‑PRC Request
Scene Context Tags
Timing Hints
PRC‑BKN Response
Goal Constraint Derivation Intent Candidates
Phrasing Hints
PRC Directive
PRC IH Response
BKN‑PRC Request
Goal Constraints
Prompt Triggers
PRC Status
PRC IH Request
BKN‑PRC Request
PRC‑BKN Response
Spatial Primitive Extraction Resolved Referents Spatial Primitives
PC‑Prompt Planner Scene Context Tags
Timing Hints
Goal Constraints
Prompt Triggers
Resolved Referents
Resolution Confidence
Spatial Primitives
Tone Profile
Phrasing Hints
PRC Directive
PRC IH Response
BKN‑PRC Request
PC‑Prompt Plan
PRC Status
PRC IH Request
BKN‑PRC Request
PRC‑BKN Response
PRC Prompt Formatter PC‑Prompt Plan
PRC Directive
PRC IH Response
BKN‑PRC Request
PRC‑BKN Response
PC Prompt
PRC Status
PRC IH Request
PRC‑BKN Response

4.5 AIMs and JSON Metadata

Table 4 gives the Prompt Creation (AIM1) and its SubAIMs (AIM2).

Table 4 – Prompt Creation (AIM1) and its SubAIMs (AIM2)

AIM1 AIM2 Name JSON
PGM‑PRC Prompt Creation X
PGM‑PTA Prompt Token Analyser X
PGM‑INI Intent Inference X
PGM‑USA User State Adaptation X
PGM‑RFR Referent Resolution X
PGM‑SCT Scene Context Tagging X
PGM‑GCD Goal Constraint Derivation X
PGM‑SPE Spatial Primitive Extraction X
PGM‑PPL PC‑Prompt Planner X
PGM‑PFM PRC Prompt Formatter X

5. JSON Metadata

https://schemas.mpai.community/PGM1/V1.0/AIMs/PromptCreation.json

6. Profiles

No Profiles.

7. Reference Software

Not part of this specification.

8. Conformance Testing

A PRC implementation conforms with Prompt Creation (PGM‑PRC) if it satisfies the conformance requirements of Table 5. Conformance Testing of the individual SubAIMs is given by the individual AIM specifications.

If a schema contains references to other schemas, conformance of data for the primary schema implies that any data referencing a secondary schema shall also validate against the relevant schema, if present, and conform with the Qualifier, if present.

Table 5 – Conformance Testing Method for the Prompt Creation (PGM‑PRC) AIM

Receives Context Descriptors Shall validate against Context Descriptors schema.
PRC Interaction History Response Shall validate against PRC Interaction History schema.
PRC Directive Shall validate against PRC Directive schema.
BKN‑PRC Request Shall validate against BKN‑PRC Interaction schema.
Produces PC Prompt Shall validate against PC Prompt schema.
PRC‑BKN Response Shall validate against BKN‑PRC Interaction schema.
PRC Interaction History Request Shall validate against PRC Interaction History schema.
PRC Status Shall validate against PRC Status schema.

9. Performance Assessment

Not part of this specification.

Go to PGM-AUA V1.0 AI Modules