1     Definition 2     Functional Requirements 3     Syntax
4     Semantics 5    Conformance Testing 6     Performance Assessment

Definition

The digital representation of an Entity’s goal-directed purpose to perform an action or to achieve a state, which may be expressed by an utterance. An Intent can be enriched by modifiers like urgency or confidence, and can be either inferred from observation of an Entity or assigned to a virtual Entity.

Functional Requirements

1. Semantic Classification: classifies Entity Intent into a two-level hierarchy:

  • Intent Category: High-level category (e.g., Informational, Procedural).
  • Intended Act: Specific intent type within the domain.

2. Execution Modifiers: supports optional parameters that refine how an Entity Intent is interpreted or executed:

  • Urgency: Priority of execution
  • ConfidenceLevel: Degree of Entity certainty
  • TemporalCue: Time-related context (e.g., “tomorrow”, “now”)
  • SpatialAnchor: Physical or virtual reference point (e.g., “that object”, “left corner”)

3. Confidence Scoring: includes a numeric confidence score representing the certainty of an Entity in classifying the Intent for use in downstream AIMs or fallback strategies based on this score.

4. Traceability: includes a Trace object with:

  • Origin: The Entity of AIM that inferred the Intent.
  • Timestamp: Time of Intent creation.

5. Uniqueness and Referencing: includes a globally unique IntentID for runtime referencing, logging, and chaining.

Syntax

https://schemas.mpai.community/MMC/V2.5/data/Intent.json

Semantics

Label Description
Header Schema header with version tag.
– Standard-Intent Fixed prefix: MMC‑EIT‑V marking the Intent data type family.
– Version Major version (1–2 digits).
– Dot-separator Character . separating version components.
– Subversion Minor version (1–2 digits).
IntentID Unique identifier for this intent instance.
IntentData Unified semantic intent object representing the Entity’s goal-directed purpose.
– IntentCategory High-level category of intent (linked to ontology: IntentCategories).
—— Informational Intent to seek or provide facts, summaries, or explanations.
—— Procedural Intent to  perform an action or procedure.
—— Expressive Intent to share emotion or opinion.
—— Interactive Intent to interact with other Entities, e.g., through requests or commands.
– IntendedAct Specific intent type within the domain. Examples:
—— Informational ask_fact, request_summary, compare_items, define_term, confirm_action, reject_suggestion, clarify_input, share_opinion, give_feedback, report_issue, query_capabilities,
—— Procedural schedule_action, trigger_behavior, modify_state, execute_command, move_object, focus_attention, highlight_area
—— Expressive express_emotion, perform_greeting, perform_gesture
—— Interactive request_help, issue_command
Modifiers Optional modifiers refining execution.
– Urgency Execution urgency (low, medium, high).
– ConfidenceLevel User certainty (tentative, neutral, assertive).
– TemporalCue Time-related signal (e.g., “now”, “later”).
– SpatialAnchor Physical reference or full spatial attitude (pose + dynamics).
ConfidenceScore Confidence in intent classification (0.0–1.0).
Trace Metadata concerning creation.
– Origin Entity or AIM that generated the intent.
– Timestamp Time the intent was created.

5     Conformance Testing

A Data instance Conforms with MPAI-MMC Intent (MMC-EIT) if:

  1.  Its JSON Object validates against its JSON Schema.
  2. Any included  JSON Object validates against its JSON Schema.
  3. All Data in the JSON Object:
    1. Have the specified Data Types.
    2. Conform with the Qualifiers signaled in their JSON Schemas.

6     Performance Assessment