Go to PGM-AUA V1.0 AI Modules

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

1 Functions

The A‑User Control (AUC) AIM:

  1. Serves as the central coordinator for Action execution, AIM orchestration, and system traceability.
  2. Governs the lifecycle of the A-User.
  3. Orchestrates the A-User interaction with
    1. The human User.
    2. The M-Instance.
    3. The M-Instance’s Processes and Items with which the A-User interacts.
  4. Sends Directive messages to AIMs to implement Instructions within the Rights the A‑User holds and the Rules applicable to the M‑Location.
  5. Tracks execution of Directives using Status messages received from A-User AIMs.

The resulting control flow ensures that the A-User operates predictably, transparently, and in alignment with human Commands, and any A-User Instructions, thus supporting life cycle integrity and enabling trust through auditable orchestration.

2. Reference Model

A-User Control:

  1. Triggers the Context Capture AIM to perceive the current M‑Location composed of a User in an M-Location.
  2. Understands scene by sending Directives to Context Enhancement, and Domain Access.
  3. Prompts Prompt Creation and the Basic Knowledge.
  4. Controls the queries made by the Basic Knowledge to Prompt Creation, Domain Access, and User State Refinement.
  5. Triggers Basic Knowledge into requesting A-User Entity State (Personality Alignment).
  6. Issues AUF Directives to the A‑User Formation AIM to produce the speaking Avatar (Persona), which will subsequently be instantiated by the A-User Control in the M-Instance.

Figure 1 gives the input/output data of A-User Control (PGM-AUC).

Figure 1 – Reference Model of A-User Control (PGM-AUC) AIM

The A-User Control AIM exercises its activity by implementing one of eight Instructions:

  1. Perception and Environment Capture (PEC): Configure perceptual subsystems to sense the responsible human in the Universe, the User in the M‑Instance, or the contents of the relevant M‑Location.
  2. Goal and Language Acquisition (GLA): Capture and segment multi-modal expressions of the responsible human and/or the User. This corresponds to giving identity and spatial relationship to the objects in the scene and to understanding the User.
  3. Prompting and Knowledge Query (PKQ): Enable structured contextual representation and semantic grounding of perceptual and state information. The A-User is now in a position to make sense of what it perceives and interprets.
  4. Goal and Intent Interpretation (GII): Based upon the results of the previous Instruction, trigger deliberative processing to determine the appropriate communicative behaviour of the A‑User. The A-User Control is now able to decide the stance it should take.
  5. Policy, Rights, and Feasibility (PRF): Validate intended behaviour with respect to governance Rules, User Entity State constraints, human commands, and domain feasibility conditions. The A-User Control knows that the A-User actions must comply with a variety of constraints.
  6. Plan Construction and Execution (PCE): Orchestrate execution of the behaviour based on Statuses reported by the AIMs, including speech and actions. The A-User Control is now able to executed the actions after taking constraints into accounts.
  7. Conflict Management and Escalation (CME): Detect unresolved inconsistencies or conflicts and escalate to the responsible human when required. Various impediments may be encountered and modifications to the action decided.
  8. Avatar Formation and Rendering (AFR): Enable synthesis and rendering of the speaking avatar. The A-User’s Avatar is formed and can be rendered.

3. Input/Output Data

The A‑User Control (PGM-AUC) AIM exchanges data types with specific purposes with the other A-User AIMs. For example, Audio Reasoning Directive is sent to Audio Spatial Reasoning and Formation Status is received from A‑User Formation.

Table 1 gives Input and Output Data of A-User Control (PGM-AUC) AIM. See below for Mapping to Unified Schema.

Table 1 – Input and Output Data of A-User Control (PGM-AUC) AIM

Input Description
Human Command From a human in the real world.
Process Action Response From a Process that has received a Process Action Request.
CXC Status Scene-level context and User presence.
CXE Status Context Enhancement spatial feasibility, occlusion, reachability flags,
PRC Status Prompt readiness, alignment status, semantic goal framing, etc.
BKN Trace Enriched response metadata and traceability, etc.
DAC Status Execution feasibility and constraint validation, etc.
USR Status Current engagement, affective tone, override flags.
PAL Status Expressive alignment, persona framing, modulation constraints, etc.
AUF Status Avatar formation success, avatar state, expressive output status.
Output Description
Action Performed by A-User on the M-Instance.
Process Action Request Request made by A-User to an M-Instance Process.
CXC Directive Instructions for perceptual acquisition.
CXE Directive Context Enhancement-related actions and sequences.
PRC Directive Prompt generation or refinement.
BKN Directive Request for knowledge retrieval or response shaping.
DAC Directive Request for domain execution.
USR Directive Request to modulate User State based on interaction feedback.
PALDirective Request for expressive modulation or Personality reconfiguration.
AUF Directive Request for avatar formation, spatial output, expressive delivery, etc.
Human Command Status A-User Control response to Human Command.

4. SubAIMs

No SubAIMs.

5. JSON Metadata

https://schemas.mpai.community/PGM1/V1.0/data/AUserControl.json

6. Profiles

No Profiles.

7. Reference Software

8. Conformance Testing

9. Performance Assessment