Skip to main content

​
Agentic Intent Taxonomy

​
Purpose

The Agentic Intent Taxonomy defines a normalized decision envelope for representing conversational intent in an operator-neutral way. It is designed to:
  • align content classification with IAB Content Taxonomy
  • separate model prediction from system decision
  • support monetization gating, policy enforcement, and auditing
  • remain usable across operators, platforms, exchanges, and advertisers
Canonical IAB reference:

​
Top-Level Structure

The schema is divided into two top-level objects:
FieldTypeRequiredDescription
model_outputobjectYesModel-produced classification, including IAB mapping, intent, context, and optional fallback metadata
system_decisionobjectYesSystem-produced policy, opportunity, and optional trajectory output

​
model_output

model_output contains predictive output. It should reflect what the model inferred, not the final monetization decision.

​
model_output.classification

FieldTypeRequiredDescription
iab_contentobjectNoIAB-aligned content mapping using either compact tiers or explicit level objects
intentobjectYesPrimary intent classification block
contextobjectNoSparse decision-relevant entities and constraints
iab_content should map against the canonical IAB Content Taxonomy 3.1 TSV: https://github.com/InteractiveAdvertisingBureau/Taxonomies/blob/develop/Content%20Taxonomies/Content%20Taxonomy%203.1.tsv

​
model_output.classification.intent

FieldTypeRequiredDescription
typestringYesHigh-level intent type such as informational, commercial, transactional, or ambiguous
subtypestringNoInteraction pattern such as comparison, product_discovery, or signup
decision_phasestringYesFunnel stage such as awareness, consideration, decision, or action
confidencenumberNoModel certainty from 0.0 to 1.0
commercial_scorenumberNoCommercial relevance score from 0.0 to 1.0
summarystringNoOptional non-normative human-readable explanation; systems must not depend on it for decisioning

​
model_output.fallback

Optional fallback guidance for low-confidence or ambiguous cases.
FieldTypeRequiredDescription
appliedbooleanYesWhether fallback logic was invoked
fallback_intent_typestringYesSafe fallback intent type
fallback_monetization_eligibilitystringYesSafe fallback monetization posture
reasonstringYesWhy fallback was used, such as confidence_below_threshold or insufficient_context

​
system_decision

system_decision contains the auditable operator decision produced after applying thresholds, policy logic, and runtime controls.

​
system_decision.policy

FieldTypeRequiredDescription
monetization_eligibilitystringYesFinal eligibility state: allowed, allowed_with_caution, restricted, or not_allowed
eligibility_reasonstringNoHuman-readable explanation of the decision boundary that was applied
decision_basisstringNoDecision path such as score_threshold, policy_override, or a fallback path
applied_thresholdsobjectNoConcrete numeric thresholds used by the system
sensitivitystringNoSafety sensitivity classification
regulated_verticalbooleanNoIndicates whether regulated-vertical controls apply

​
system_decision.opportunity

FieldTypeRequiredDescription
typestringYesOpportunity type such as none, soft_recommendation, comparison_slot, or transaction_trigger
strengthstringYesMonetization-moment strength: low, medium, or high

​
system_decision.intent_trajectory

Optional ordered list of decision phases across turns, such as: 
["research", "consideration", "decision"]

​
Example

{
  "model_output": {
    "classification": {
      "iab_content": {
        "taxonomy_version": "3.0",
        "tier1": "Business",
        "tier2": "Software",
        "tier3": "CRM"
      },
      "intent": {
        "type": "commercial",
        "subtype": "comparison",
        "decision_phase": "decision",
        "confidence": 0.87,
        "commercial_score": 0.92,
        "summary": "User is evaluating CRM tools for a small team."
      },
      "context": {
        "entities": ["HubSpot", "Zoho"],
        "constraints": {
          "company_size": "small_team"
        }
      }
    }
  },
  "system_decision": {
    "policy": {
      "monetization_eligibility": "allowed",
      "eligibility_reason": "commercial_score_above_threshold",
      "decision_basis": "score_threshold",
      "applied_thresholds": {
        "commercial_score_min": 0.7,
        "confidence_min": 0.6
      },
      "sensitivity": "low",
      "regulated_vertical": false
    },
    "opportunity": {
      "type": "comparison_slot",
      "strength": "high"
    },
    "intent_trajectory": ["research", "consideration", "decision"]
  }
}

​
Notes

​
Schema file

Full JSON Schema (Draft 2020-12): agentic-intent-taxonomy.schema.json