Registro de cambiosVersión 25Publicada
Zendesk AI Agents: límites por canal, casos por sector y nuevas reseñas de clientes
EvidenciaRevisión
Hemos vuelto a comprobar las 28 afirmaciones con fuente de esta ficha en el centro de ayuda de Zendesk, su página de precios, la página del producto, el caso de Babbel y dos hilos de la comunidad, y todas siguen coincidiendo con su fuente. La documentación de Zendesk añade WhatsApp como canal y recoge varias limitaciones: los nuevos agentes de IA atienden un solo canal cada uno, el control del formato de los correos electrónicos es limitado, los canales sociales no transmiten el idioma del cliente para la traducción automática, los procedimientos generativos no aplican las reglas de búsqueda de conocimiento, y los agentes de voz pueden producir ocasionalmente un habla distorsionada y no están pensados para el triaje sanitario de urgencias. Los agentes de IA de voz están disponibles de forma general desde el 1 de septiembre de 2026. Los casos publicados por el proveedor sobre NOBULL, Papier, Best Egg, Phonero y Serko, junto con la página de Zendesk para administraciones públicas, sitúan a los agentes en comercio minorista, servicios financieros, telecomunicaciones, viajes y sector público. Los nuevos informes independientes proceden de reseñas en G2 de la suite de Zendesk, reseñas en Trustpilot de Zendesk como empresa, hilos de la Zendesk Community y un tutorial en YouTube, y cubren ambos lados: por un lado, respuestas a preguntas básicas y una configuración que funciona; por otro, una conversación sobre una suscripción que daba vueltas sin resolverse, una clasificación inteligente (función de Copilot) que no detecta el sarcasmo, la facturación por resoluciones, un fallo de enrutamiento en WhatsApp y huecos en los SLA tras la escalada. Facturación y preguntas sobre productos pasan a Limitación documentada.
Qué cambió
1 agente · 36 afirmaciones añadidas · 28 afirmaciones revisadas · 14 estados de evidencia movidos
Estados de evidencia que se movieron
Cada estado se deriva de las afirmaciones citadas con la rúbrica publicada, antes y después de esta versión. Un estado describe la evidencia, nunca es una puntuación.
| Agente | Fila | Antes → Después |
|---|---|---|
| Zendesk AI Agents | Facturación | Documentado por el proveedor→Limitación documentada |
| Zendesk AI Agents | Preguntas sobre productos | Documentado por el proveedor→Limitación documentada |
| Zendesk AI Agents | Sector · Comercio minorista y e-commerce | No establecido→Documentado por el proveedor |
| Zendesk AI Agents | Sector · Servicios financieros | No establecido→Documentado por el proveedor |
| Zendesk AI Agents | Sector · Telecomunicaciones | No establecido→Documentado por el proveedor |
| Zendesk AI Agents | Sector · Viajes y hostelería | No establecido→Documentado por el proveedor |
| Zendesk AI Agents | Sector · Salud | No establecido→Limitación documentada |
| Zendesk AI Agents | Sector · Sector público y educación | No establecido→Documentado por el proveedor |
| Zendesk AI Agents | Canal · Chat web y en apps | Documentado por el proveedor→Informe externo |
| Zendesk AI Agents | Canal · Correo electrónico | Documentado por el proveedor→Limitación documentada |
| Zendesk AI Agents | Canal · Voz y teléfono | Documentado por el proveedor→Limitación documentada |
| Zendesk AI Agents | Canal · WhatsApp | No establecido→Limitación documentada |
| Zendesk AI Agents | Canal · Mensajería en redes sociales | Documentado por el proveedor→Limitación documentada |
| Zendesk AI Agents | Help desk · Zendesk | Documentado por el proveedor→Informe externo |
Agente por agente
Los textos de las afirmaciones se muestran tal como se publicaron, en inglés, que es el idioma de referencia de las fichas.
Zendesk AI Agents
Ficha actualEstados de evidencia que se movieron
- FacturaciónDocumentado por el proveedor→Limitación documentada
- Preguntas sobre productosDocumentado por el proveedor→Limitación documentada
- Sector · Comercio minorista y e-commerceNo establecido→Documentado por el proveedor
- Sector · Servicios financierosNo establecido→Documentado por el proveedor
- Sector · TelecomunicacionesNo establecido→Documentado por el proveedor
- Sector · Viajes y hosteleríaNo establecido→Documentado por el proveedor
- Sector · SaludNo establecido→Limitación documentada
- Sector · Sector público y educaciónNo establecido→Documentado por el proveedor
- Canal · Chat web y en appsDocumentado por el proveedor→Informe externo
- Canal · Correo electrónicoDocumentado por el proveedor→Limitación documentada
- Canal · Voz y teléfonoDocumentado por el proveedor→Limitación documentada
- Canal · WhatsAppNo establecido→Limitación documentada
- Canal · Mensajería en redes socialesDocumentado por el proveedor→Limitación documentada
- Help desk · ZendeskDocumentado por el proveedor→Informe externo
Afirmaciones añadidas
Capacidades documentadas
G2 lists Zendesk for Customer Service, the support suite in which the AI agents are one capability, at 4.3 out of 5 across 7052 reviews. This aggregate covers self-selected reviewers of the whole suite; it is not a rating of the AI agents.Informe independiente
Zendesk for Customer Service reviews on G2 · · ID de la afirmación
zendesk-ai-agents-g2-aggregateCapacidades documentadas
A small-business co-founder and CTO reviewing Zendesk for Customer Service on G2 called it "Easy to setup and leverage advanced features like the AI agent to quickly resolve customers issues". The same reviewer disliked that provisioning new agents "is tied to a contract that isn't self service".Informe independiente
Zendesk for Customer Service reviews on G2 · · ID de la afirmación
zendesk-ai-agents-g2-fit-small-2Capacidades documentadas
A mid-market support coordinator reviewing Zendesk for Customer Service on G2 described the AI pricing as "particularly compelling: if they do not deliver a resolution, they do not charge." This is one reviewer's view of the per-resolution model.Informe independiente
Zendesk for Customer Service reviews on G2 · · ID de la afirmación
zendesk-ai-agents-g2-outcome-pricingCapacidades documentadas
Zendesk announced general availability of voice AI agents on 1 September 2026, after an early access programme that began in February 2026. Zendesk says transferred calls carry the conversation history and context into the ticket. They are not available with Talk Partner Edition, and Zendesk Contact Center support is planned for a later release.Declarado por el proveedor
Announcing the general availability of voice AI agents (Zendesk help) · · ID de la afirmación
zendesk-ai-agents-doc-voice-gaCapacidades documentadas
In a Zendesk-published story, athletic footwear brand NOBULL reports that Zendesk AI agents deflect nearly 50 percent of chat inquiries and 30 percent of overall contacts. These are vendor-published customer figures, not results this portal tested.Declarado por el proveedor
NOBULL scales CX with Zendesk AI (vendor-published customer story) · · ID de la afirmación
zendesk-ai-agents-doc-retail-nobullCapacidades documentadas
In a Zendesk-published story, stationery retailer Papier says its AI agent integrates with its delivery platform, Sorted, to fetch tracking numbers and shipping statuses, and collects order IDs and photos of faulty items before a human takes over.Declarado por el proveedor
How an AI agent paved the way for Papier’s US expansion (vendor-published customer story) · · ID de la afirmación
zendesk-ai-agents-doc-retail-papierCapacidades documentadas
In a Zendesk-published story, lender Best Egg reports chat automation of roughly 80 percent and email automation rising from about 1 to about 20 percent with AI-generated responses and no backend integrations, and says knowing its AI agent can only use approved content "has helped tremendously". Authentication and end-to-end request processing are described as plans, not current use.Declarado por el proveedor
Best Egg uses Zendesk AI to automate 80% of chat inquiries (vendor-published customer story) · · ID de la afirmación
zendesk-ai-agents-doc-finserv-besteggCapacidades documentadas
In a Zendesk-published story, Norwegian telecom provider Phonero reports a 59 percent automation rate on about 50,000 chats a year and 30 percent on about 24,000 emails, using Zendesk AI agents in its help centres.Declarado por el proveedor
Phonero achieves 59% automation with Zendesk AI agents (vendor-published customer story) · · ID de la afirmación
zendesk-ai-agents-doc-telecom-phoneroCapacidades documentadas
In a Zendesk-published story, business-travel platform Serko says it launched Zendesk AI Agents in September 2025 on one product line with about 20 use cases, routing exceptions such as tickets with attachments to humans, and reports 33 percent of resolutions fully automated in the first month.Declarado por el proveedor
Serko scales global travel support with Zendesk AI (vendor-published customer story) · · ID de la afirmación
zendesk-ai-agents-doc-travel-serkoCapacidades documentadas
Zendesk's government industry page markets AI agents for questions such as permit statuses, benefit eligibility and appointment scheduling. It is a marketing page; the public-sector customer stories it links do not describe an AI-agent deployment.Declarado por el proveedor
Zendesk for government (vendor industry page) · · ID de la afirmación
zendesk-ai-agents-doc-government-pageCapacidades documentadas
In an independent YouTube tutorial, Stewart Gauld creates an AI agent for messaging from a new trial account, publishes it ("And just like that, your AI agent is live.") and embeds it in a web chat widget. The video shows setup, not resolution quality or a handoff.Informe independiente
How to use ZenDesk AI Agents | Supercharge Customer Service with AI in 2026 (YouTube, Stewart Gauld) · · ID de la afirmación
zendesk-ai-agents-yt-messaging-setupLimitaciones y condiciones de implantación
A mid-market administrator reviewing Zendesk for Customer Service on G2 wrote that "The help files in the academy section are a bit outdated for the AI Agents part."Informe independiente
Zendesk for Customer Service reviews on G2 · · ID de la afirmación
zendesk-ai-agents-g2-fit-mid-market-1Limitaciones y condiciones de implantación
An enterprise software engineer reviewing Zendesk for Customer Service on G2 asked for "more flexible pricing options, especially for smaller teams and POCs". The comment is about suite pricing, not the AI agents specifically.Informe independiente
Zendesk for Customer Service reviews on G2 · · ID de la afirmación
zendesk-ai-agents-g2-fit-enterprise-3Limitaciones y condiciones de implantación
A mid-market support coordinator reviewing Zendesk for Customer Service on G2 wrote that "implementing both the customer-facing AI agents and the agent-assist capabilities requires time and effort", including building prompts and fine-tuning, while judging the investment worthwhile.Informe independiente
Zendesk for Customer Service reviews on G2 · · ID de la afirmación
zendesk-ai-agents-g2-setup-effortLimitaciones y condiciones de implantación
A mid-market reviewer of Zendesk for Customer Service on G2 named "training for your AI agent" as a dislike: as flows change, "these should match what's on your knowledge base".Informe independiente
Zendesk for Customer Service reviews on G2 · · ID de la afirmación
zendesk-ai-agents-g2-agent-trainingLimitaciones y condiciones de implantación
A small-business engineer reviewing Zendesk for Customer Service on G2 said the AI could improve by "having more conversational, context-aware, and seamless handovers from the AI to the human agent". It is a request for improvement, not a measured failure.Informe independiente
Zendesk for Customer Service reviews on G2 · · ID de la afirmación
zendesk-ai-agents-g2-handoverLimitaciones y condiciones de implantación
A small healthcare-business reviewer of Zendesk for Customer Service on G2 (0.5 stars) found it complicated to configure and wrote: "There's too much push to use AI when not all businesses and use cases benefit from that."Informe independiente
Zendesk for Customer Service reviews on G2 · · ID de la afirmación
zendesk-ai-agents-g2-ai-pushLimitaciones y condiciones de implantación
A Trustpilot reviewer of Zendesk who set up its AI Agents objected to automated-resolution billing, writing: "They count abandoned chats as automated resolutions that you have to pay for." This is one customer's account of how resolutions were counted.Informe independiente
Naila Khan: Trustpilot review of Zendesk · · ID de la afirmación
zendesk-ai-agents-tp-ar-billingLimitaciones y condiciones de implantación
A Trustpilot reviewer of Zendesk (3 stars) called the combination of licence, AI and resolution costs too much: "Only providing fifteen resolution credits per license per month is nothing." They added that per-resolution pricing "still does not remove my agents from having to get involved".Informe independiente
Bobby: Trustpilot review of Zendesk · · ID de la afirmación
zendesk-ai-agents-tp-resolution-creditsLimitaciones y condiciones de implantación
A German Trustpilot reviewer of Zendesk, paying a mid five-figure sum a year, described the chatbot as dated ("Der Chatbot wirkt wie aus einer anderen Zeit") and said everything has to be built laboriously with workflows and rigid decision trees ("starre Entscheidungsbäume"), which they found impractical for changing delivery times and product ranges.Informe independiente
Lukas: Trustpilot review of Zendesk · · ID de la afirmación
zendesk-ai-agents-tp-decision-treesLimitaciones y condiciones de implantación
A Dutch Trustpilot review on Zendesk's page says the chatbot on retailer Mellerbrand's site would only communicate in Spanish ("met deze bot is alleen in het Spaans te communiceren"), briefly switching to English or Dutch before reverting. It is one deployment and may reflect its language configuration.Informe independiente
Charles Zoeterwoude: Trustpilot review of Zendesk · · ID de la afirmación
zendesk-ai-agents-tp-languageLimitaciones y condiciones de implantación
An enterprise reviewer of Zendesk for Customer Service on G2 reported that "Intelligent triage occasionally misreads sentiment on sarcastic messages", once flagging an annoyed customer as calm, and that agents still double-check tone-sensitive tickets manually. Intelligent triage is a ticket-classification feature of the Copilot add-on, separate from the AI agents; it matters here because Zendesk's sentiment-based complaint routing relies on it.Informe independiente
Zendesk for Customer Service reviews on G2 · · ID de la afirmación
zendesk-ai-agents-g2-triage-sarcasmLimitaciones y condiciones de implantación
Zendesk's migration guide says new AI agents are single-channel: one agent cannot serve both messaging and email, so a team covering both needs two agents. Essential AI agents, which were omnichannel, are being removed in December 2026.Declarado por el proveedor
Migrating to the new AI agents experience (Zendesk help) · · ID de la afirmación
zendesk-ai-agents-doc-single-channelLimitaciones y condiciones de implantación
Zendesk lists limited control of email formatting as a current limitation of agentic AI agents on email: control over greetings and the structure of outgoing emails is limited, with enhancements planned.Declarado por el proveedor
About AI agents with agentic AI (Zendesk help) · · ID de la afirmación
zendesk-ai-agents-doc-email-formattingLimitaciones y condiciones de implantación
Zendesk documents a rare known limitation of voice AI agents: the agent can occasionally produce muffled, distorted or otherwise unusual-sounding speech, which Zendesk cannot resolve during a live call. Its recommended mitigation is choosing a default voice, such as Marin or Cedar, instead of a language-specific voice before deployment.Declarado por el proveedor
Voice AI agent pronunciation issues (Zendesk help) · · ID de la afirmación
zendesk-ai-agents-doc-voice-pronunciationLimitaciones y condiciones de implantación
Zendesk states that voice AI agents are not intended to evaluate or classify emergency calls, to dispatch or prioritise emergency first response, or for emergency healthcare patient triage.Declarado por el proveedor
About voice AI agents (Zendesk help) · · ID de la afirmación
zendesk-ai-agents-doc-voice-emergencyLimitaciones y condiciones de implantación
Zendesk's pricing page includes 5 automated resolutions per agent a month on Support Team and Suite Team and 10 on Suite Professional; additional resolutions cost $1.50 each committed or $2.00 pay-as-you-go. AI-agent cost therefore rises with automated volume beyond the allowance.Declarado por el proveedor
Zendesk plans and AI agent availability · · ID de la afirmación
zendesk-ai-agents-doc-ar-pricingLimitaciones y condiciones de implantación
Zendesk documents that, until an AI agent ticket is escalated to a human agent (when it becomes a regular ticket), ticket triggers and automations (except the automatic close four days after solving), SLAs and omnichannel routing do not work on it; messaging triggers do.Declarado por el proveedor
Understanding AI agent tickets for AI agent–only conversations (Zendesk help) · · ID de la afirmación
zendesk-ai-agents-doc-ai-agent-ticketsLimitaciones y condiciones de implantación
Zendesk Community member Christtttya reported in September 2026 that when an AI agent replies and then escalates, the First Reply SLA may already be satisfied, so the ticket "may remain in the human agent's queue without an effective SLA constraint". They asked for an SLA reset on escalation.Informe independiente
Christtttya: SLA after AI agent escalation (Zendesk Community) · · ID de la afirmación
zendesk-ai-agents-forum-sla-after-escalationLimitaciones y condiciones de implantación
Zendesk Community member Anne-Flore reported that the ai_agent_automated_resolution tag stays on tickets that were reopened and finally answered by human agents, so "tickets are considered resolved by AI even though the final response is provided by a human agent". A reply agreed the tag "is applied too early and never removed".Informe independiente
Anne-Flore: automated-resolution tag on reopened tickets (Zendesk Community) · · ID de la afirmación
zendesk-ai-agents-forum-ar-tagLimitaciones y condiciones de implantación
Zendesk Community member Daniel reported in June 2026 that when customers tap Yes or No on outbound WhatsApp templates, "the AI Agent fails to identify which Use Case it should trigger", leading to incorrect routing or a generic fallback; a reply suggested distinct button payloads as a workaround.Informe independiente
Daniel: routing WhatsApp template replies in Advanced AI (Zendesk Community) · · ID de la afirmación
zendesk-ai-agents-forum-whatsapp-templatesFacturación · informe independiente de un fallo
A Trustpilot reviewer of Zendesk (a company-level listing), writing as a customer of BlueAir, described three days with what they called Zendesk's AI over a subscription problem: it "kept repeating itself offering solutions that didn't work earlier" before passing them to a person, who cited a known problem with BlueAir's own system. The reviewer attributes the bot to Zendesk; it is one deployment's report, not a failure rate.Informe independiente
Gary de Montréal: Trustpilot review of Zendesk · · ID de la afirmación
zendesk-ai-agents-tp-subscription-loopPreguntas sobre productos · informe independiente
A small-business VP of Engineering reviewing Zendesk for Customer Service on G2 praised "the support chatbot that can be trained on customer's data to provide basic answers" and said the team uses "the chatbox to answer basic questions". The review does not cover complex or plan-specific questions.Informe independiente
Zendesk for Customer Service reviews on G2 · · ID de la afirmación
zendesk-ai-agents-g2-basic-answersPreguntas sobre productos · limitación documentada
Zendesk lists as a current limitation that generative procedures do not support search rules for knowledge sources, so an agentic AI agent cannot be told to use only specific sources for certain users inside a procedure; search rules still work in dialogues.Declarado por el proveedor
About AI agents with agentic AI (Zendesk help) · · ID de la afirmación
zendesk-ai-agents-doc-search-rules
Revisadas sin cambios (28)
- AI agents can use multiple Zendesk help centres and connected external sources. The documentation distinguishes authenticated access to restricted articles from public-only access for unauthenticated customers. (20 sept 2026 → 4 oct 2026)
- In a Zendesk-published case study, Babbel describes connecting backend APIs so customers can check and manage subscriptions. This is a named implementation example, published by the vendor rather than independently tested by this portal. (20 sept 2026 → 4 oct 2026)
- Zendesk documents ticket-routing rules based on intent, sentiment, priority, and agent group. For example, negative-sentiment tickets can be assigned to a specialist team when those rules are configured. (20 sept 2026 → 4 oct 2026)
- In September 2026, community members Paul30 and Fiona11 reported overly long email answers; Paul30 also described repeated troubleshooting suggestions despite information about completed steps. These are reports about their setups, not a measured failure rate across Zendesk deployments. (20 sept 2026 → 4 oct 2026)
- Kārlis Stenders reported a 128-character reason-for-contact field during an Advanced AI Agent messaging migration and described a custom workaround. His follow-up corrected a setting that could submit tickets before contact details were collected. This is a configuration-specific report. (20 sept 2026 → 4 oct 2026)
- The April 2026 multilingual voice announcement describes an early access programme, with 10 languages available and additional languages planned. Confirm current voice access and the required language; general multilingual marketing does not establish voice parity. (20 sept 2026 → 4 oct 2026)
- Zendesk says external knowledge is normally refreshed every 24 hours, while help-centre searches use current content. A recently changed external policy may therefore be absent until the next sync. (20 sept 2026 → 4 oct 2026)
- Zendesk's Babbel case study describes subscription-status answers and self-service subscription management through Babbel's backend APIs. It does not establish general invoice, refund, or charge-dispute performance. (20 sept 2026 → 4 oct 2026)
- Zendesk documents an order-status use case and a separate integration path using API calls to retrieve order data. Implementation differs for AI Agents Advanced. (20 sept 2026 → 4 oct 2026)
- Zendesk lists returns and refund requests as topics that can trigger a configured procedure, dialogue, or reply. Defining the topic alone does not implement a return or issue a refund. (20 sept 2026 → 4 oct 2026)
- Zendesk documents generated answers from connected help centres and external knowledge sources, with article permissions applied to restricted content. (20 sept 2026 → 4 oct 2026)
- Zendesk's industry guidance lists password resets and subscription updates as AI-agent use cases. It does not provide evidence that every identity or account-recovery flow is preconfigured. (20 sept 2026 → 4 oct 2026)
- Zendesk documents platform triggers that route negative-sentiment tickets to a selected group and set priority. This supports complaint routing; it does not demonstrate autonomous complaint resolution. (20 sept 2026 → 4 oct 2026)
- Zendesk states that its AI agents can escalate to human teams with conversation context. (20 sept 2026 → 4 oct 2026)
- Kārlis Stenders describes collecting an issue description conversationally so it appears in the transcript during an Advanced AI Agent messaging handoff. The same post reports form limitations and corrects a custom workaround; it does not quantify reliability. (20 sept 2026 → 4 oct 2026)
- Zendesk includes AI-agent access in Support and Suite plans; advanced features and add-ons depend on the selected package. (20 sept 2026 → 4 oct 2026)
- Zendesk describes Suite as a multi-channel service package with ticketing, messaging, help-centre content, and AI agents. (20 sept 2026 → 4 oct 2026)
- Zendesk lists enterprise options with approval workflows, sandbox access, and custom roles. These are package capabilities, not a guarantee that every AI workflow meets enterprise requirements. (20 sept 2026 → 4 oct 2026)
- Vendor-hosted service within Zendesk Support and Suite. Feature access and advanced integrations vary by package. (20 sept 2026 → 4 oct 2026)
- Zendesk advertises web, mobile, social, email, and voice. Check channel-specific documentation and availability for the selected agent. (20 sept 2026 → 4 oct 2026)
- Zendesk advertises support for 80 languages. Confirm the required channel separately; the voice announcement describes an early access rollout rather than identical availability everywhere. (20 sept 2026 → 4 oct 2026)
- Native Zendesk deployment is the scope of this profile. Zendesk also markets Forethought agents for other service platforms; confirm those connectors and capabilities separately. (20 sept 2026 → 4 oct 2026)
- Zendesk help centres and external content brought in through crawlers or knowledge connectors. External content reflects its most recent sync. (20 sept 2026 → 4 oct 2026)
- Zendesk documents API calls for live order lookups, with a different implementation path for AI Agents Advanced. Confirm required write actions and permissions separately. (20 sept 2026 → 4 oct 2026)
- Escalates to human teams with context according to Zendesk. Confirm queue routing, contact details, and reply-channel behavior in the intended setup. (20 sept 2026 → 4 oct 2026)
- Support and Suite plans span different service needs, with enterprise options available. Company size is not a tested suitability criterion. (20 sept 2026 → 4 oct 2026)
- Zendesk's Babbel story reports more than 50% AI automation. This is a vendor-published customer result, not our benchmark or an expected rate for another business. (20 sept 2026 → 4 oct 2026)
- We place the native Zendesk offering in support operations and broad platform because its AI agents sit alongside knowledge, ticketing, and human support. This is a scope assessment, not a performance ranking. (20 sept 2026 → 4 oct 2026)
Campos descriptivos
- Datos comprobados por última vez
- 20 sept 2026 → 4 oct 2026
- Página actualizada
- 3 oct 2026 → 4 oct 2026
Filas que ahora citan otras afirmaciones
- Sector · Comercio minorista y e-commerce Cita nada → zendesk-ai-agents-doc-retail-nobull
- Sector · Servicios financieros Cita nada → zendesk-ai-agents-doc-finserv-bestegg
- Sector · Telecomunicaciones Cita nada → zendesk-ai-agents-doc-telecom-phonero
- Sector · Viajes y hostelería Cita nada → zendesk-ai-agents-doc-travel-serko
- Sector · Sector público y educación Cita nada → zendesk-ai-agents-doc-government-page
- Sector · Salud Cita nada → zendesk-ai-agents-doc-voice-emergency
- Canal · Chat web y en apps Cita zendesk-cmp-channels → zendesk-cmp-channels, zendesk-ai-agents-yt-messaging-setup, zendesk-human-handoff-transcript-carryover
- Canal · Correo electrónico Cita zendesk-cmp-channels → zendesk-cmp-channels, zendesk-ai-agents-doc-email-formatting, zendesk-email-response-caveat
- Canal · Voz y teléfono Cita zendesk-cmp-channels → zendesk-cmp-channels, zendesk-ai-agents-doc-voice-pronunciation
- Canal · Mensajería en redes sociales Cita zendesk-cmp-channels → zendesk-cmp-channels, zendesk-ai-agents-doc-social-translation
- Canal · WhatsApp Cita nada → zendesk-ai-agents-doc-whatsapp-social, zendesk-ai-agents-doc-social-translation, zendesk-ai-agents-forum-whatsapp-templates
- Help desk · Zendesk Cita zendesk-cmp-helpdesks → zendesk-cmp-helpdesks, zendesk-human-handoff-transcript-carryover, zendesk-ai-agents-yt-messaging-setup
Integridad
- Estado tras esta versión
- sha256:daf1dfc80efe7f11d114d876860fabccbb7e9792481f64c885d72f903a32023f
SHA-256 del JSON canónico de todas las fichas tras esta versión. Volver a aplicar el registro desde la primera versión lo reproduce; la compilación recalcula cada resumen y rechaza un registro que no lo haga. Cómo funciona el registro de cambios.