| Function | Reference Model | Input/Output Data |
| SubAIMs | JSON Metadata | Profiles |
| Reference Software | Conformance Testing | Performance Assessment |
1. Function
The A‑User Control (AUC) AIM:
- Serves as the central coordinator for Action execution, AIM orchestration, and system traceability.
- Governs the lifecycle of the A-User.
- Orchestrates the A-User interaction with
- The human User.
- The M-Instance.
- The M-Instance’s Processes and Items with which the A-User interacts.
- Sends Directive messages to AIMs to implement Instructions within the Rights the A‑User holds and the Rules applicable to the M‑Location.
- 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:
- Triggers the Context Capture AIM to perceive the current M‑Location composed of a User in an M-Location.
- Understands scene by sending Directives to Audio Spatial Reasoning, Visual Spatial Reasoning, and Domain Access).
- Prompts Prompt Creation and the Basic Knowledge.
- Controls the queries made by the Basic Knowledge to Prompt Creation, Domain Access, and User State Refinement.
- Triggers Basic Knowledge into requesting A-User Entity State (Personality Alignment).
- Issues Formation 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:
- Perception and Capture Control: Configure the perceptual system for sensing the human in their universe Location, the User in their M-Instance Location, and the M-Location.
- Goal Acquisition: Capture and validate multimodal expressions of the human and/or the User to extract the Raw Goal Expression.
- Prompting and Knowledge Queries: Prompt to clarify and ground all steps after Raw Goal Expression has been determined.
- Goal Interpretation and Intent: Normalise, ground, and interpret the human and/or User goal using Domain and User information.
- Policy, Rights and Feasibility: Check the interpreted Goal against M-Instance Rules, User Entity State constraints and domain feasibility.
- Plan Construction and Execution: Construct an action plan and orchestrate its execution in the metaverse.
- Conflict Management and Escalation: Detect inconsistencies or conflicts and resolve or escalate them as necessary.
- Avatar Formation and Rendering: Produce the final natural‑language speech and avatar‑based multimodal output.
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. |
| Context Capture Status | Scene-level context and User presence. |
| Audio Action Status | Audio spatial feasibility, occlusion, reachability flags, etc. |
| Visual Action Status | Visual spatial constraints and scene anchoring, etc. |
| Prompt Plan Status | Prompt readiness, alignment status, semantic goal framing, etc. |
| BK Response Trace | Enriched response metadata and traceability, etc. |
| DA Action Status | Execution feasibility and constraint validation, etc. |
| User State Status | Current engagement, affective tone, override flags. |
| Personality Alignment Status | Expressive alignment, persona framing, modulation constraints, etc. |
| Formation 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. |
| Context Capture Directive | Instructions for perceptual acquisition. |
| Audio Action Directive | Audio-related actions and sequences. |
| Visual Action Directive | Visual-related actions and sequences. |
| Prompt Creation Directive | Prompt generation or refinement. |
| BK Query Directive | Request for knowledge retrieval or response shaping. |
| DA Action Directive | Request for domain execution. |
| User State Status | Request to modulate User State based on interaction feedback. |
| Personality Alignment Directive | Request for expressive modulation or Personality reconfiguration. |
| Formation 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.