'the more than 1,200 available on the Marketplace'
Limitations
Assisted escalations and contained resolutions are not deducted from the allowance; a contained resolution is one the language-model check could not confirm.
Paying only for verified resolutions ties cost to outcome, but Zendesk’s language model decides what counts as verified — ask how you can audit that classification.
ETHORITY analysis
Technical foundations
AI agents and features inside the Zendesk service suite.
Per verified automated resolution: since 18 May 2026 Zendesk distinguishes assisted escalations, contained resolutions and verified resolutions; only verified resolutions draw from the resolution allowance. A language model checks each conversation.
No price per resolution and no overage price in the documentation reviewed. Allowances per plan under the new tiers are not stated in the article; accounts still on the previous model had 5–15 included resolutions per agent per month.
Zendesk names SOC 2 Type II, ISO 27001:2022, 27017, 27018, 27701, FedRAMP LI-SaaS, PCI DSS, HIPAA and HDS. Its scope page lists AI Agents in scope for ISO 27001, SOC 2 and HDS, and partly for FedRAMP; PCI scope for AI features is not stated.
Model providers named: AWS Bedrock, Microsoft Azure, Groq, Fireworks AI, OpenAI, Google Gemini, ElevenLabs; zero-data-retention endpoints; OpenAI European endpoints
'No data is stored by the LLM provider following the delivery of the output.'
Retention and deletion
Service Data deletion starts 90 days after cancellation (9 months after unconverted trial); deletion takes 40-120 days by product (AI agents - Advanced 120, Forethought AI Agents 90); backups e.g. 130 days ticketing, 14 days AI agents - Advanced; no expedited deletion
'We do not offer expedited deletion of Service Data.' Policy effective June/July 2026. LLM endpoints zero data retention per Generative AI article.
Export
Account export in JSON, CSV, XML (admins; must be enabled by Zendesk Support; Suite Growth+ / Support Professional+; not Team plans); REST API on all plans; AI agent tickets cannot be exported
'Use cases, generative replies, and agentic AI fully support any of the languages in the list below.'
Questions for the provider
Ask the provider whether your data is used to train models and which consent controls apply.
Ask the provider for the price, billing unit and required commitment for your scope.
Cost per accepted outcome
Editable hypothetical example · not provider pricing or measured performance. Use this monthly worksheet to test your own quote and quality assumptions.
/ accepted outcome
accepted outcomes / month
5,000 tasks × 80% = 4,000 accepted outcomes per month. Higher entered costs raise unit cost; more accepted outcomes spread the same cost over more results.
Formula: entered monthly costs ÷ (monthly tasks × acceptance % ÷ 100). The numerator includes only the costs you enter. Add applicable licence, usage, integration, human review and rework costs yourself; this is not automatically a fully loaded estimate or a vendor billing model. Capacity released is not realized financial value.
Inputs stay in this browser tab’s session, including reload and language changes. They are not added to the page URL. Continuing prepares an unsent enquiry draft.
A written comparison of up to three AI offerings · €195 net
You get the facts that matter for your decision, each with its source, the questions to ask each vendor and a cost estimate based on your own numbers. First you agree your three most important criteria with Sten Franke.
We deliver your brief by email within a maximum of five working days after payment is confirmed and we have agreed the question and minimum information needed to begin. ETHORITY confirms the start date and delivery date and delivers earlier when the reviewed brief is ready. Missing optional information is recorded and assessed; it does not require you to research the solution yourself. Review before delivery and email support are included.
ETHORITY®