PGM-AUA V1.0 AIMs - Prompt Planning and Formatting

Go to PGM-AUA V1.0 AI Modules

Function

Ref. Model

1. Function

The Prompt Planning and Formatting (PGM‑PPF) AIM assembles all evidence produced by the upstream Sub-AIMs of the Prompt Creation AIM, forming a structured PC Prompt and managing the multi-turn MCP session with the Basic Knowledge AIM.

PGM‑PPF:

Assembles the Intent, Propositions, Goal, and Personality received from the upstream Sub-AIMs into a PC Prompt and submits it to the Basic Knowledge AIM.
Manages the multi-turn MCP session with the Basic Knowledge AIM, receiving BKN-PRC Requests and issuing BKN-PRC Responses as needed throughout the session. Multiple request–response exchanges may occur within a single session.
Multiplexes the AUC-PRC Response signals received from the Prompt Token Analysis, Intent and Referent Analysis, and Prompt Contextualisation AIMs, forming the composite AUC-PRC Response output signal to be passed to A‑User Control.
Multiplexes the PRC Interaction History Requests received from the Prompt Token Analysis, Intent and Referent Analysis, and Prompt Contextualisation AIMs, forming the composite PRC Interaction History Request output signal, with one field per Sub-AIM.
Queries the Private Storage via PRC Interaction History Requests when prior interaction context is needed to inform prompt assembly or session management.

PGM‑PPF does not perform linguistic analysis, intent inference, referent resolution, or goal and expressive configuration derivation. Rather, it receives fully derived evidence from the upstream Sub-AIMs and is responsible solely for prompt assembly, session management, and signal multiplexing.

2. Reference Model

Figure 1 depicts the Reference Model of the Prompt Planning and Formatting (PGM‑PPF) AIM.

Figure 1 – The Prompt Planning and Formatting (PGM‑PPF) AIM

3. Input/Output Data

Table 1 specifies the Input and Output Data of the Prompt Planning and Formatting (PGM‑PPF) AIM.

Table 1 – I/O Data of the Prompt Planning and Formatting (PGM‑PPF) AIM

Input	Description
Intent	Structured representation of the User’s goal-directed purpose, produced by the Intent and Referent Analysis AIM.
Proposition	Fully resolved referential expressions and scene context produced by the Intent and Referent Analysis and Prompt Contextualisation AIMs.
Goal	Structured representation of the objectives, priorities, and constraints produced by the Prompt Contextualisation AIM.
Personality	Expressive configuration carrying tone, style, pacing, and narrative goal produced by the Prompt Contextualisation AIM.
AUC-PRC Request	Request from the A‑User Control AIM specifying scope, depth, and policy constraints for prompt construction.
PRC Interaction History Response	Interaction History Response from Private Storage providing prior interaction context to inform prompt assembly or session management.
BKN-PRC Request	Query issued by the Basic Knowledge AIM during an active MCP session, requesting additional context or clarification. May be received multiple times within a session.
AUC-PRC Response	Multiplexed status signals received from the Prompt Token Analysis, Intent and Referent Analysis, and Prompt Contextualisation AIMs.
PRC Interaction History Request	Multiplexed Interaction History Requests received from the Prompt Token Analysis, Intent and Referent Analysis, and Prompt Contextualisation AIMs.
Output	Description
PC Prompt	Structured prompt submitted to the Basic Knowledge AIM to open the MCP session, assembling Intent, Propositions, Goal, and Personality into a single coherent prompt.
BKN-PRC Response	Response to a BKN-PRC Request received from the Basic Knowledge AIM during the session. May be sent multiple times within a session.
AUC-PRC Response	Composite status signal assembling the processing outcomes of all Sub-AIMs.
PRC Interaction History Request	Composite Interaction History Request assembling the requests of all Sub-AIMs.

4. Sub-AIMs

No Sub-AIMs.

5. JSON Metadata

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

6. Profiles

No Profiles.

7. Reference Software

Not part of this specification.

8. Conformance Testing

Table 2 provides the Conformance Testing Method for the Prompt Planning and Formatting (PGM‑PPF) AIM.

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 2 – Conformance Testing Method for the Prompt Planning and Formatting (PGM‑PPF) AIM

Receives	Intent	Shall validate against the Intent schema.
	Proposition	Shall validate against the Proposition schema.
	Goal	Shall validate against the Goal schema.
	Personality	Shall validate against the Personality schema.
	AUC-PRC Request	Shall validate against the AUC-PRC Request schema.
	PRC Interaction History Response	Shall validate against the PRC Interaction History schema.
	BKN-PRC Request	Shall validate against the BKN-PRC schema, with Mode RQ.
	AUC-PRC Response	Shall validate against the AUC-PRC Response schema. Each Sub-AIM field shall be present.
	PRC Interaction History Request	Shall validate against the PRC Interaction History schema. Each Sub-AIM field shall be present.
Produces	PC Prompt	Shall validate against the PC Prompt schema.
	BKN-PRC Response	Shall validate against the BKN-PRC schema, with Mode RS.
	AUC-PRC Response	Shall validate against the AUC-PRC Response schema. All Sub-AIM fields and the PGM‑PPF field shall be populated.
	PRC Interaction History Request	Shall validate against the PRC Interaction History schema. All Sub-AIM fields shall be present.

9. Performance Assessment