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 constructs a structured prompt suitable for submission to Basic Knowledge (LLM) by analysing the contextual descriptors of the current interaction, inferring the User’s intent, resolving referents, contextualising the prompt with scene and goal constraints, and formatting the result into a PC Prompt that opens a multi-turn MCP session with Basic Knowledge.

Prompt Creation:

  1. Operates on the Context Descriptors produced by Context Description, the Text Object received from the environment, the PRC Directive received from A‑User Control, the PRC IH Response resulting from queries made to A‑User Storage, and the BKN-PRC Request received from Basic Knowledge during an active session.
  2. Performs a multi‑stage prompt construction process including token analysis, intent and referent analysis, prompt contextualisation, and prompt planning and formatting, without performing deliberative reasoning or final response generation.
  3. Produces the PC Prompt sent to Basic Knowledge to open the MCP session, the BKN-PRC Response sent to Basic Knowledge in reply to queries received during the session, the PRC Status sent to A‑User Control, and the PRC IH Request when querying interaction history from A‑User Storage.

The PC Prompt carries the structured representation of the User’s intent, resolved referents, scene context, goal constraints, and expressive configuration required by Basic Knowledge to generate a response.

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 lists 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 Structured descriptors of the current interaction context produced by Context Description.
Text Object Text input received from the environment representing the User’s utterance or query.
PRC Directive Directive from A‑User Control specifying scope, depth, and policy constraints for prompt construction.
PRC IH Response Interaction History response from A‑User Storage providing relevant past interaction context to support prompt construction.
BKN-PRC Request Query issued by Basic Knowledge to Prompt Creation during an active MCP session, requesting additional context or clarification. May be received multiple times within a session.
Output Description
PC Prompt Structured prompt submitted to Basic Knowledge to open the MCP session, carrying intent, resolved referents, scene context, goal constraints, and expressive configuration.
BKN-PRC Response Response from Prompt Creation to a BKN-PRC Request received from Basic Knowledge during the session. May be sent multiple times within a session.
PRC Status Multiplexed status signals from the internal Sub-AIMs reporting their processing outcomes.
PRC IH Request Multiplexed Interaction History requests from the internal Sub-AIMs issued to A‑User Storage.

4. Sub-AIMs (Informative)

This section is informative. The decomposition into Sub-AIMs 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 AIM receives Context Descriptors, a Text Object, and the PRC Directive, and progressively transforms them into a structured PC Prompt through a sequence of specialised Sub-AIMs.

The external inputs and control signals are fed to the appropriate Sub-AIMs:

  1. The Prompt Token Analyser Sub-AIM parses the Text Object and Context Descriptors into a Meaning structure carrying POS tagging, named entity tagging, dependency structure, and semantic role labelling results. It queries A‑User Storage via PRC IH to retrieve relevant past interaction context.
  2. The Intent and Referent Analysis Sub-AIM operates on the Meaning to infer the User’s intent, producing an Intent carrying category, action type, spatial anchors, and confidence score. It simultaneously resolves referential expressions to scene Entities, expressing the result as Propositions linking subjects, predicates, and objects with their spatial and temporal context. It queries Basic Knowledge via BKN-PRC and A‑User Storage via PRC IH as needed.
  3. The Prompt Contextualisation Sub-AIM enriches the Intent and Propositions with goal constraint derivation, scene context tagging, and user state adaptation, producing a Goal carrying objectives, priorities, and trigger conditions, a Personality carrying the expressive configuration (tone, style, pacing, narrative goal), and additional scene Propositions representing contextual tags and timing guidance. It queries Basic Knowledge via BKN-PRC and A‑User Storage via PRC IH as needed.
  4. The Prompt Planning and Formatting Sub-AIM assembles all derived evidence — Intent, Propositions, Goal, and Personality — into a PC Prompt and submits it to Basic Knowledge. It manages the multi-turn MCP session with Basic Knowledge, receiving BKN-PRC Requests and issuing BKN-PRC Responses as needed throughout the session. It also multiplexes the PRC Status and PRC IH Request signals from all Sub-AIMs into the corresponding external output signals.

Each of Intent and Referent Analysis, Prompt Contextualisation, and Prompt Planning and Formatting independently generates a PRC Status and a PRC IH Request, which are multiplexed by Prompt Planning and Formatting into the corresponding external output signals.

4.3 Functions of Sub-AIMs

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

Table 2 – Functions of the Sub-AIMs of the Prompt Creation (PGM‑PRC) Composite AIM

Name Function
Prompt Token Analyser Parses the Text Object and Context Descriptors into a Meaning structure carrying POS tagging, named entity tagging, dependency structure, and semantic role labelling results, querying A‑User Storage via PRC IH to retrieve relevant past interaction context.
Intent and Referent Analysis Infers the User’s Intent from the Meaning, and resolves referential expressions to scene Entities, expressing results as Propositions, querying Basic Knowledge via BKN-PRC and A‑User Storage via PRC IH as needed.
Prompt Contextualisation Enriches the Intent and Propositions with goal constraint derivation, scene context tagging, and user state adaptation, producing a Goal, a Personality carrying the expressive configuration, and additional scene Propositions, querying Basic Knowledge via BKN-PRC and A‑User Storage via PRC IH as needed.
Prompt Planning and Formatting Assembles Intent, Propositions, Goal, and Personality into a PC Prompt, manages the multi-turn MCP session with Basic Knowledge, and multiplexes the PRC Status and PRC IH Request signals from all Sub-AIMs into the corresponding external outputs.

4.4 Input/Output Data of Sub-AIMs

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

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

Name Input Data Output Data
Prompt Token Analyser Text Object
Context Descriptors
PRC Directive
PRC IH Response		 Meaning
PRC Status
PRC IH Request
Intent and Referent Analysis Meaning
PRC Directive
PRC IH Response
BKN-PRC Response		 Intent
Proposition
PRC Status
PRC IH Request
BKN-PRC Request
Prompt Contextualisation Intent
Proposition
PRC Directive
PRC IH Response
BKN-PRC Response		 Goal
Personality
Proposition
PRC Status
PRC IH Request
BKN-PRC Request
Prompt Planning and Formatting Intent
Proposition
Goal
Personality
PRC Directive
PRC IH Response
BKN-PRC Request
PRC Status (multiplexed from all Sub-AIMs)
PRC IH Request (multiplexed from all Sub-AIMs)		 PC Prompt
BKN-PRC Response
PRC Status
PRC IH Request

4.5 AIMs and JSON Metadata

Table 4 gives the Prompt Creation (AIM1) and its Sub-AIMs (AIM2).

Table 4 – Prompt Creation (AIM1) and its Sub-AIMs (AIM2)

AIM1 AIM2 Name JSON
PGM‑PRC Prompt Creation X
PGM‑PTA Prompt Token Analyser X
PGM‑IRA Intent and Referent Analysis X
PGM‑PCX Prompt Contextualisation X
PGM‑PPF Prompt Planning and Formatting 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:

  1. The implementation includes all Sub-AIMs listed in Table 2.
  2. All I/O Data listed in Table 1 are present and conform with their respective Data Types.
  3. All Sub-AIM I/O Data listed in Table 3 conform with their respective Data Types.
  4. The implementation produces a PC Prompt that integrates the outputs of Intent and Referent Analysis and Prompt Contextualisation.
  5. The implementation correctly manages the multi-turn BKN-PRC session, issuing a BKN-PRC Response in reply to each BKN-PRC Request received from Basic Knowledge.

9. Performance Assessment

Not part of this specification.

Go to PGM-AUA V1.0 AI Modules