HubSpot Breeze Customer Agent — resolutionOutcome contract

HubSpot charges 50 credits (USD 0.50) per resolved conversation on text-based channels. The Knowledge Base defines a resolution as a conversation with at least one customer-agent reply that shares a content source or performs an action, and no qualifying (visitor-initiated) handoff to a human within 72 hours of the last visitor response.

Contract ID: hubspot_breeze_customer_agent_resolution
Source: https://knowledge.hubspot.com/customer-agent/analyze-your-customer-agents-performance
Retrieved: 2026-09-11
Notes: Price: https://www.hubspot.com/products/artificial-intelligence/credits and https://legal.hubspot.com/hubspot-product-and-services-catalog (retrieved 2026-09-11): 50 credits × USD 0.010. INFERRED: that the Knowledge Base 'Resolutions' metric is the definition used for credit billing (the credits page says 'resolved conversation' without cross-referencing it). The 'agent reply shares a content source or performs an action' condition is vendor-internal and not observable from systems of record, so the vendor lens encodes only the 72h no-handoff rule and is at least as permissive as the vendor's own count.

Vendor lens

Reproduces the vendor's published definition as closely as public documentation allows.

Verified if all of: escalated to a human within 72h of the claim; no customer reply within 72h of the claim
Not verified if any of: escalated to a human within 72h of the claim; a duplicate claim exists for the same subject in the period
Unverifiable if any of: required fact source not connected: conversations

Strict lens

Applies the same definition with longer windows and additional checks a controller would expect.

Verified if all of: customer confirmed resolved within 30d of the claim
Not verified if any of: reopened within 30d of the claim; escalated to a human within 7d of the claim; a human agent replied within 7d of the claim; a refund or credit was issued within 30d of the claim; customer left a negative satisfaction rating; a duplicate claim exists for the same subject in the period
Unverifiable if any of: required fact source not connected: conversations; subject could not be matched in any fact source
Override (supporting evidence only): transcript label is customer_indicated_unresolved, abandoned → NOT_VERIFIED

Unknown fields

Things the source has not published. No value is assumed for these.

agent_reply_with_source_or_action
reopen_handling

Contract YAML

The machine-readable contract compiled into both lenses. Sign in to select it for your tenant or fork it.

# HubSpot Breeze Customer Agent — 50 credits (USD 0.50) per resolved conversation on text-based channels.
id: hubspot_breeze_customer_agent_resolution
version: 1
vendor: hubspot
vendor_display: "HubSpot Breeze Customer Agent"
outcome_type: resolution
claim_source: hubspot.customer_agent_resolutions
subject_kind: conversation
description: >
  HubSpot charges 50 credits (USD 0.50) per resolved conversation on text-based channels. The Knowledge Base defines a
  resolution as a conversation with at least one customer-agent reply that shares a content source or performs an
  action, and no qualifying (visitor-initiated) handoff to a human within 72 hours of the last visitor response.
source_citation:
  url: "https://knowledge.hubspot.com/customer-agent/analyze-your-customer-agents-performance"
  retrieved: "2026-09-11"
  title: "Analyze customer agent's performance - HubSpot Knowledge Base"
  notes: >
    Price: https://www.hubspot.com/products/artificial-intelligence/credits and
    https://legal.hubspot.com/hubspot-product-and-services-catalog (retrieved 2026-09-11): 50 credits × USD 0.010.
    INFERRED: that the Knowledge Base 'Resolutions' metric is the definition used for credit billing (the credits page
    says 'resolved conversation' without cross-referencing it). The 'agent reply shares a content source or performs an
    action' condition is vendor-internal and not observable from systems of record, so the vendor lens encodes only the
    72h no-handoff rule and is at least as permissive as the vendor's own count.
unknown_fields: [reopen_handling, agent_reply_with_source_or_action]
lenses:
  vendor:
    verified_if:
      all:
        - not: {escalated_to_human_within: "72h"}
        - no_customer_reply_within: "72h"
    not_verified_if:
      any:
        - escalated_to_human_within: "72h"
        - duplicate_claim_for_subject
    unverifiable_if:
      any:
        - missing_fact_source: [conversations]
  strict:
    verified_if:
      all:
        - customer_confirmed_resolved: {within: "30d"}
    not_verified_if:
      any:
        - reopened_within: "30d"
        - escalated_to_human_within: "7d"
        - human_reply_within: "7d"
        - refund_or_credit_within: "30d"
        - csat_negative
        - duplicate_claim_for_subject
    unverifiable_if:
      any:
        - missing_fact_source: [conversations]
        - identity_unmatched
    overrides:
      - when: {transcript_label_is: [customer_indicated_unresolved, abandoned]}
        verdict: NOT_VERIFIED
exclusions:
  - channel_in: [voice, phone]
billing:
  unit_price: 0.50
  currency: USD

Use this contract See it applied in a sample statement