> For the complete documentation index, see [llms.txt](https://library.zoom.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://library.zoom.com/business-services/zoom-virtual-agent/zoom-virtual-agent-admin-experience.md).

# Admin Experience

Explore Zoom Virtual Agent architecture, configuration, integrations, and behavior for voice and chat agents.

### Voice and Chat Agentic AI Core Concepts

The following sections detail the core concepts of the next-generation Zoom Virtual Agent across both voice and chat.

#### <mark style="color:blue;">Each agentic voice and chatbot has a unique identity designed to assist a specific audience with questions, problems, or concerns</mark>

The components described below center on a proprietary AI Runtime Service and its supporting infrastructure, each of which plays a distinct role in enabling intelligent, automated, and context-aware conversational interactions.

#### <mark style="color:blue;">Core Components of the Voice Agent</mark>

<div data-with-frame="true"><img src="https://1175968039-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FctBXUMeBy4rtLMmMkKRG%2Fuploads%2FlKJVeyvdypF2H1XBHhbl%2Funknown.png?alt=media&amp;token=47f425de-2763-4a04-bc20-1e938f3e77c2" alt=""></div>

This section outlines the foundational components that enable the intelligent and automated behavior of the next-generation Zoom Virtual Agent when deployed in a voice-based environment. Like the chat agent, the system is centered on the AI Runtime Service and its interconnected components, which collectively allow for agentic decision-making, language processing, and action execution across digital channels.

**An AI Runtime Service orchestrates reasoning, memory, and action across the system**

The AI Runtime Service is the central orchestration layer for Zoom Virtual Agent. It handles:

* **Input interpretation**: Receives user voice input, processes it through speech-to-text, and determines intent.
* **Decisioning**: Applies business logic and routing rules to decide the next best action.
* **Integration management**: Coordinates with knowledge systems, tools, and models to assemble responses or initiate workflows.
* **Agentic behaviors**: Supports automated task execution, context tracking, and conversational adaptability without requiring human oversight.

The runtime backend includes key conversation controls such as end-turn detection, barge-in detection, filler response generation, and error-handling guardrails.

The voice framework continually improves how these controls behave in live conversations. Recent enhancements make conversations feel more responsive and better paced, and make handoffs more reliable: the agent re-engages more intelligently when a caller goes quiet, paces responses to avoid dead air, and completes transfers to live agents cleanly even when a caller keeps talking. These improvements apply automatically to every ZVA agent and require no admin configuration.

**The Worker-Talker Framework enables parallel processing during voice interactions**

Traditional voice agents must pause conversations to execute backend tasks, creating delays. The Worker-Talker architecture separates these responsibilities.

The Talker Agent maintains a continuous conversation with the end user. The Worker Agent executes backend operations—like tool calls, data retrievals, and reasoning tasks—in parallel. Both the Talker and Worker Agents access unified context, including conversation history, customer variables, and real-time updates. The Worker streams partial results to the Talker so conversation continues during background tasks.

Administrators don’t configure the Worker-Talker split directly. It operates within the AI Runtime Service. This means that Skills and Tools involving long-running API calls won’t cause conversation pauses or timeouts.

**Knowledge Base Systems enable retrieval-augmented question and answering**

The next-generation Zoom Virtual Agent uses Retrieval-Augmented Generation (RAG) to improve the factual accuracy of its responses:

* **Enterprise knowledge access**: Connects to structured and unstructured data repositories, such as help centers or internal documentation.
* **Dynamic retrieval**: During conversations, the agent retrieves relevant knowledge snippets to answer factual or policy-driven questions.
* **Scalability**: Knowledge Base Systems can scale across multiple brands, product lines, or customer segments with granular control.

Admins can configure knowledge connectors and manage document indexing via the Zoom Virtual Agent admin portal.

**LLM Gateway facilitates access to large language model intelligence**

This component enables the Zoom Virtual Agent to:

* **Send prompts** to external or internal models based on user utterances.
* **Receive generated completions** that help with complex language understanding, multi-turn reasoning, and open-ended dialog.
* **Decouple orchestration logic** from specific models, enabling flexibility and model management.

The gateway provides a standardized interface for routing requests, supporting both Zoom-hosted and third-party models.

**Third-Party Text-to-Speech enables natural, conversational delivery**

Once the AI Runtime assembles a text-based response, that response is sent to a text-to-speech engine for audio rendering. This system:

* **Converts text to speech in real time** to support live conversations.
* **Allows for custom voice selection** to match brand personality or accessibility needs.
* **Supports multilingual output** to enhance usability across global deployments.

Integrations with major providers enable flexibility in voice quality, languages, and deployment options.

The voice agent's text-to-speech infrastructure also includes automatic failover monitoring and recovery. The system continuously monitors latency and failure rates across TTS providers and automatically switches to a backup provider if the primary service experiences failures. Once the primary provider recovers, the system reverts automatically. This process operates without administrator configuration.

**Zoom Skills and Tools and Third-Party Tools extend the system's ability to take action**

The next-generation Zoom Virtual Agent goes beyond answering questions by enabling task completion:

* **Zoom Skills and Tools**: Native integrations with the Zoom ecosystem (e.g., Zoom Contact Center, Zoom Scheduler, Zoom Revenue Accelerator) for actions like escalation, booking, or analytics tagging.
* **Third-Party Tools**: Extend functionality beyond Zoom through integrations with external systems and applications. Customers can choose from:
  * **Prebuilt third-party tools developed by Zoom**: Available for quick setups.
  * **Custom third-party tools built by customer developers using AI Studio**: Offering greater flexibility and tailored integrations with CRM, IT Service Management (ITSM), ticketing, or other business platforms.

These tools allow a virtual agent to execute business processes without transferring the conversation to a human agent.

#### <mark style="color:blue;">Core Components of the Chat Agent</mark>

<div data-with-frame="true"><img src="https://1175968039-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FctBXUMeBy4rtLMmMkKRG%2Fuploads%2F08VkWHgV3U7KGjmuj1U0%2Funknown.png?alt=media&amp;token=4ee83542-5b06-4b0f-8e71-0ae118543954" alt=""></div>

This section outlines the foundational components that enable the intelligent and automated behavior of the next-generation Zoom Virtual Agent when deployed in a chat-based environment. Like the voice agent, the system is centered on the AI Runtime Service and its interconnected components, which collectively allow for agentic decision-making, language processing, and action execution across digital channels.

**AI Runtime Service governs the full lifecycle of digital interactions**

The AI Runtime Service coordinates the decisioning, data access, and tool integrations needed to power intelligent chat interactions. It performs:

* **Input interpretation**: Message parsing and intent recognition from chat inputs.
* **Decisioning**: Business logic execution to guide task fulfillment, conditional flows, or escalation.
* **Integration management**: Integration with knowledge sources and tooling to support rich, responsive conversations.
* **Agentic behaviors**: Supports automated task execution, context tracking, and conversational adaptability without requiring human oversight.

The service also manages context tracking, error recovery, conversation pacing, and fallback strategies to provide resilient experiences.

The AI Runtime Service also leverages parallel processing for backend voice operations. See the [Core Components of the Voice Agent](#core-components-of-the-voice-agent) section for more detail.

**Knowledge Base Systems enable retrieval-augmented question and answering**

During chat interactions, the next-generation Zoom Virtual Agent can:

* **Query** enterprise knowledge repositories in real time based on user messages.
* **Retrieve** the most relevant snippets using semantic or keyword-based matching.
* **Generate** contextual responses using the retrieved information and the LLM Gateway.

This approach enhances accuracy so answers are grounded in enterprise-approved content.

**LLM Gateway supports dynamic natural language processing and response generation**

The LLM Gateway acts as the abstraction layer between the AI Runtime Service and connected large language models. It allows the runtime to:

* **Route** prompts to multiple LLMs for flexible reasoning capabilities.
* **Access** model outputs to interpret complex questions, summarize articles, or generate multi-sentence responses.
* **Switch or upgrade** model providers without altering orchestration logic.

This structure enables secure and scalable use of generative AI in enterprise workflows.

**Third-Party LLMs provide diverse language models and customization options**

Through the LLM Gateway, organizations can:

* **Select models** optimized for their domain or use case (e.g., support, HR, product onboarding).
* **Control latency** and cost-performance tradeoffs by matching models to intents or traffic segments.
* **Choose providers** based on organizational requirements and available data residency options.

These integrations support a plug-and-play ecosystem for evolving AI strategies.

**Zoom Skills, Tools, and Third-Party Tools enable real-time action and workflow execution**

Next-generation Zoom Virtual Agent does more than respond—it takes action in real time through near-seamless integrations:

* **Zoom Skills and Tools**: Native integrations with the Zoom ecosystem (e.g., Zoom Scheduler, Zoom Contact Center) empower the agent to route users, book meetings, escalate interactions, or tag feedback automatically.
* **Third-Party Tools**: Extend automation beyond Zoom by connecting to external systems and applications. These include:
  * **Prebuilt third-party tools developed by Zoom**: enabled with a single click for rapid activation and faster outcomes.
  * **Custom third-party tools built by customer developers using AI Studio**: Offering deeper customization and flexible integrations with CRM, ITSM, ticketing, or other enterprise platforms.

This empowers organizations to resolve customer needs quickly, without escalation.

**Engagement Runtime Service manages experience delivery and system coordination**

In the chat agent flow, the Engagement Runtime Service handles:

* **Session state management** to maintain context across turns.
* **Transcript generation and logging**, which are forwarded to file storage.
* **Testing hooks and admin tooling** for conversation flow validation.

It helps virtual agents perform reliably, consistently, and with an auditable trail in live environments.

**Web-based chat offers flexible access to Zoom Virtual Agent**

Account owners and admins can enable an immersive chat experience on desktop and tablet devices.

* **Windows open centered on the screen**, keeping users focused on their conversation.
* **Background interaction can be disabled** by an admin to reduce accidental exits.

**A digital front door gives campaigns a branded welcome screen**

Account owners and administrators can configure a branded welcome screen for Zoom Virtual Agent campaigns, giving consumers a structured, professional entry point before an engagement begins. The welcome screen embeds on a brand's website through a no-code interface and supports chat agents. Administrators control the screen's branding image, announcement text, description, hours of operation, form input fields, and secondary resources such as a Terms of Use link.

For multi-language campaigns, administrators can select assets from the asset library for every text field in the digital front door's styles configuration, including greeting text, call-to-action buttons, card titles, form labels, link names, article descriptions, and text blocks. At runtime, each consumer sees localized text based on their detected language, so a single digital front door can serve customers in multiple languages. Single-language campaigns continue to use manual text entry. For configuring the chat agent itself in multiple languages, see [Zoom Virtual Agent supports multiple languages and dialects](#zoom-virtual-agent-supports-multiple-languages-and-dialects)

**Multimodal virtual agents can process uploaded images and documents in chat conversations**

Account owners and administrators can enable chat agents to process uploaded images and documents in chat conversations. Voice agents can even receive file uploads via SMS mid-call. Virtual Agent extracts text from screenshots and files in JPEG, PNG, HEIC, WEBP, and PDF formats. Customers can upload receipts, error screens, serial number labels, and other documents instead of manually typing information.

The system presents extracted information summaries and asks for customer confirmation before proceeding. When text extraction is unclear or incomplete, the agent provides clarifying questions to verify accuracy. Importantly, this means the agent isn't designed to silently extract and act on content. Instead, it confirms with the customer first before proceeding.

During interactions with a customer, Zoom Voice Agent can create and send a file upload link using SMS for attachment uploads. Upload links are active only during the call and expire automatically when the engagement ends. Any uploaded attachments are mapped back to the engagement and appear in transcripts and analytics.

Zoom Virtual Agent also includes content guardrails that is designed to detect inappropriate and AI-generated images uploaded during conversations. The system analyzes uploads in real time and responds with predefined messages when restricted content is identified. If someone repeatedly uploads inappropriate material, those violations trigger automatic escalation to a human agent. These content guardrails are enabled by default and don’t require admin configuration.

{% hint style="info" %}
**Note**

This feature requires activation by Zoom. Contact your Zoom account team to enable this capability. Also, admins should confirm data-handling compliance requirements for image uploads in their environment.
{% endhint %}

#### <mark style="color:blue;">Agent Guidance is an agent’s foundational identity, defining its tone, purpose and capabilities</mark>

The Agent Guidance feature in Zoom Virtual Agent defines an identity by setting its tone, purpose, capabilities, and operational boundaries. Administrators can create guidance using industry-specific prebuilt templates, which streamline and accelerate drafting custom guidance for other use cases.

For example, if an admin configures Agent Guidance with a warm, conversational tone, it will respond to users with understandable language. If it's configured with strict, to-the-fact guidance, it will respond coldly and directly.

To configure Agent Guidance, administrators specify the agent’s role, define the tasks it should perform, and review supported and unsupported scenarios. Zoom AI generates an initial draft that can be refined to meet your unique requirements. The built-in **Prompt Assistant** helps simplify this process by enabling users of all experience levels to optimize and refine prompts. This offers clear, effective guidance for every agent.

While guidance establishes high-level behavior, the agent’s effectiveness depends on alignment with its knowledge base and skills.

**Agent Architect builds a full agent from a plain-language description**

The new and improved Agent Architect lets account owners and admins build a fully capable Zoom Virtual Agent by describing what they need in plain language. Admins enter their requirements in the prompt, and Agent Architect generates a structured set of agent instructions without requiring a template or manual setup.

A right-hand panel keeps every generated decision transparent: recommended skills, a suggested voice with the reasoning behind it, inferred tools alongside their configuration status, detected variables, and clarifying questions raised from the brief. Admins keep shaping the agent through a persistent sidebar, and follow-up instructions refine the draft in place without restarting the flow. Drafts are testable immediately — even when some tools aren't fully configured yet — so admins can validate the shape of the agent before wiring up every downstream integration.

**Agent Architect improvement upgrades**

The agent improvement experience in Agent Architect includes three upgrades:

* **Visible processing and tool execution**: Processing updates and tool operations are visible during the active turn. Each tool appears as a single item with a readable name, moves from **Running** to **Completed**, and displays in execution order. Raw chain-of-thought and tool results stay hidden by design.
* **Complete conversational tool coverage for Receptionist**: Outbound SMS, Transfer by Name, and Scheduling are conversationally authorable, matching Voice Agent coverage. Agent Architect handles general configuration and finite choices, while account-specific inputs — senders, route targets, URLs, and variables — remain user-controlled in Review/Edit. Missing details leave the draft incomplete rather than fabricated.
* **Existing-only variables with guided placeholder flow**: Agent Architect no longer creates variables automatically. Every binding must resolve to an existing, authorized variable. Unresolved references become placeholders that users resolve through the Skill Library's guided selection. Final Apply is blocked until every binding is valid, and tool fields that require variables (such as the SMS recipient and scheduling link) stay empty until explicitly bound.

{% hint style="info" %}
**Note**

This feature requires activation by Zoom. Contact your Zoom account team to enable this capability.
{% endhint %}

**A simplified agent detail page surfaces the most-used settings**

The agent detail page has been reorganized so the settings administrators use most — such as voice actor and greeting — sit front and center, while less frequently adjusted options are grouped under a dedicated Advanced section. All existing functionality stays intact; the layout just makes routine configuration easier to navigate and shortens onboarding for new administrators. Because this layout is enabled by default, no activation is required.

**Administrators can select and manage the AI model that powers an agent**

Account owners and administrators can choose the AI model behind an agent from a dropdown of available certified models in the agent's Advanced settings. Before a model change is saved, a confirmation prompt appears so the switch is deliberate — results can vary between models, so Zoom recommends testing prompts and instructions against the selected model before using it in production. New accounts start on the latest certified default model, while existing accounts keep their current model until an administrator changes it.

Zoom also gives administrators notice before a model is retired. When a model an agent uses is scheduled for deprecation, the agent's settings surface the deprecation date and a suggested replacement, and administrators receive at least 30 days' notice before the change takes effect. Once a model is fully removed, it no longer appears in the picker.

**Receptionist onboarding offers a guided way to get started**

Receptionist onboarding gives admins a faster, lower-effort path to a working agent — a guided alternative to the more admin-intensive traditional bot-building process. Rather than configuring every component by hand, admins move through a recommended-skills flow that stands up common capabilities in a few steps.

Admins can connect their Google, Outlook, or Apple calendar and stand up a Zoom Scheduler booking page in a single step inside the Zoom Virtual Agent onboarding flow. Selecting the **Scheduling** skill during the recommended-skills step opens an embedded Scheduler wizard that handles calendar connection, availability, and booking-page creation end to end, so the receptionist can book against real, up-to-date availability from day one. On completion, a confirmation panel surfaces the connected calendar, a pre-filled meeting-type description, and a dropdown to select or add booking pages. Admins who already have Zoom Scheduler booking pages can pick one from the list instead of creating a duplicate.

Callers can also book appointments using their phone number as the primary identifier, matching how they already reach the receptionist. Email is no longer required by default, though it can still be captured as an optional secondary field if the caller shares it. For appointments originally booked with email as the identifier, a fallback email lookup remains in place during the transition so existing bookings stay retrievable. Appointments made with a phone number as the key identifier also receive an SMS directly from Zoom Scheduler, giving the caller ways to confirm, reschedule, or cancel.

#### <mark style="color:blue;">Knowledge Bases are sources of intelligent answers for agentic bots</mark>

Zoom Virtual Agent delivers accurate answers through a three-step process: retrieval, augmentation, and generation (RAG). When a user submits a question, the system first retrieves the most relevant information from the Knowledge Base, grounding the response in factual, company-specific data. This retrieved content is then augmented and paired with the user’s original query to provide the language model with precise context. Finally, the model generates a natural, coherent, and contextually relevant response for the end user.

**Understanding the Virtual Agent Knowledge Base**

Zoom Virtual Agent relies on its Knowledge Base to provide consistent, accurate answers that align with company policies. Administrators have several integration options to populate the Knowledge Base:

* **API Integrations**: Automatically sync knowledge articles from sources like Zendesk, ServiceNow, and Zoom Docs.
* **Manual Integration**: Upload content such as PDFs and CSVs, or create and edit articles directly within the web interface.
* **Web Sync**: Use web crawling to ingest FAQs and knowledge articles from public sites, with customizable extraction via JavaScript.

This flexible approach allows organizations to either leverage their existing knowledge management systems or build directly within the Zoom ecosystem.

**Retrieval-Augmented Generation (RAG)**

Zoom Virtual Agent incorporates Retrieval-Augmented Generation (RAG), which grounds AI responses in Knowledge Base content for accuracy and contextual relevance. This new version operates on Zoom AI's unified single-stack infrastructure while maintaining consistent Knowledge Base integration methods. This architecture enhances scalability, performance, and integration across AI tools for a consistent experience for both end users and administrators.

**Best practices for knowledge content**

The effectiveness of an agent hinges on the quality of its Knowledge Base. Administrators must strategically curate this content, prioritizing consistency and appropriateness while regularly removing outdated or irrelevant information. Each article should focus on a single, distinct topic and provide complete context to answer related questions. Avoid splitting topics across multiple articles or combining unrelated topics, as this diminishes retrieval clarity.

A clear, one-topic-per-article structure enables a Virtual Agent to retrieve the most relevant information efficiently. To minimize ambiguity, content should employ concise, structured sentences and simple language. Location-dependent references like “see above” should be replaced with explicit identifiers for further clarity.

**Knowledge Bases can be created using a variety of options, including certain pre-built/custom API integrations, web sync, or manually**

Customers can create or add to an existing Knowledge Base using a variety of options, including:

* API Integrations with Zendesk, ServiceNow, Salesforce, Kustomer, Freshdesk, or Confluence. For more information on integrations, see the Zoom Support article [Understanding Virtual Agent knowledge base sync types](https://support.zoom.com/hc/en/article?id=zm%5Fkb\&sysparm%5Farticle=KB0075644).
* Web sync from publicly available websites, via sitemap, URL upload, and link discovery (JavaScript extraction supported upon enablement request).

**Customers can have separate Knowledge Bases for manual and CRM content**

Although a Knowledge Base can’t mix manual and integrated content, accounts can create multiple Knowledge Bases for different content. For example, an account creates one Knowledge Base for API-integrated articles, and a second Knowledge Base for manual article uploads.

**A virtual agent can draw on multiple Knowledge Bases at once**

Separate Knowledge Bases don't have to sit on different agents. In the current version of Zoom Virtual Agent, an administrator can assign multiple Knowledge Bases of different types directly to a single agent, so one agent draws on both manually curated and integration-sourced content within the same engagement.

Knowledge Base Groups — the mechanism previously used to bundle multiple Knowledge Bases together in ZVA 1.0 — don't apply to the latest version of Zoom Virtual Agent. You can't assign a Knowledge Base Group to an agent in the current version. Instead, you assign the individual Knowledge Bases directly.

**Knowledge Bases are subject to various limitations, depending on their type**

Knowledge Bases are subject to various limitations depending on the Knowledge Base type. These limitations are discussed below:

**General Knowledge Bases**

* An account can have a total of 100 Knowledge Bases. This can be any combination of manually curated, API-connected, or web-based Knowledge Bases.

**Knowledge Base Articles**

* The text file size for an article (including HTML) can't exceed 50,000 characters.
* Only basic HTML (styling such as bold, hyperlinks, `<div>` tags, etc.) is supported. Advanced HTML, like script tags, are removed upon saving your content.
* Tables are not supported at this time and are removed upon save actions.

**Manual Knowledge Bases**

* Manual KBs are limited to 5,000 articles per Knowledge Base.

**API-Connected Knowledge Bases**

There are no unique restrictions for this type of Knowledge Base.

**Web Sync Connected Knowledge Bases**

* Web KBs are limited to 5,000 articles per Knowledge Base.
* Web Sync can ingest content using sitemap sync, Link discovery, or URL upload.
* Web Sync will only detect up to 250 sitemap URLs.
* There is a 60-second timeout when fetching sitemaps and individual pages. The AI-based crawler option has a 30-second timeout.
* The sitemap crawler employs the user-agent header “Zoom KB Crawler.” This can be used to add a crawler being blocked by your system to an approved list.
* Each article has a 250 MB ingestion size limit and a 10 MB text size limit (excluding image data).

**General Syncing**

The sync task includes built-in timeouts for reliability and performance. The longest individual task is **index creation**, which has a **30-minute timeout**. If index creation exceeds this limit, the task will fail and must be restarted.

Administrators can also configure periodic sync schedules (e.g., daily or weekly) to automatically keep the content up to date with the source system. In addition, built-in validation tools allow admins to run queries against the knowledge base before deploying it to production, helping verify the accuracy and performance of the KB component independently.

#### <mark style="color:blue;">Skills and Tools help virtual agents deliver empathetic, contextual conversations while enabling the automated resolution of complex issues</mark>

**Introduction to the Tool Library**

The Zoom Virtual Agent Tool Library allows the system to connect with external platforms through APIs. In large language model (LLM) terminology, ‌which Zoom also refers to as third-party models, a Tool represents a defined method for retrieving data from or sending data to third-party systems. This enables Virtual Agents to go beyond static knowledge bases by dynamically interacting with external services, providing more accurate and actionable responses during conversations.

**Using Tools to manage external data**

Tools are designed to provide precise control when retrieving or updating information. Instead of relying on the third-party model to parse complex or lengthy API responses, Tools allow administrators to define exactly which data fields should be returned. This approach reduces ambiguity, improves reliability, and enables Virtual Agents to deliver consistent answers without being overloaded by unnecessary or irrelevant API payloads.

**Handling sensitive and excessive data**

When integrating with external systems, APIs may return sensitive information such as PII or large amounts of unnecessary data. The Tool Library supports the use of JavaScript to manipulate responses before passing them to the third-party model. Administrators can filter, transform, or delete fields to keep only the essential information. This helps limit the exposure of sensitive data, avoids overwhelming the model, and streamlines the interaction between Virtual Agents and third-party services.

**Best practices for Tool configuration**

Administrators should design with simplicity and precision in mind. Use cases that involve retrieving specific values, such as a case ID or order status, benefit most from Tool-driven integrations. By narrowing the response scope, Tools can perform targeted actions while minimizing the complexity pushed into the third-party model context. Each Tool should be tailored to its use case and tested against the APIs it connects to for consistent behavior across different scenarios.

**Test cases prefill and validate tool inputs before publishing**

Administrators can validate what an API call or custom script Tool returns before wiring it into a live flow. In the Tool's preview panel, a Test cases tab lets administrators create and save named test cases — each name up to 30 characters — that store input-parameter values across all supported data types. When running the debug, administrators can select a saved test case to prefill the input parameters (the last-used test case carries over automatically) or enter values manually, then run the debug to confirm the Tool behaves as expected. This removes the need to retype sample inputs on every debug run and lets administrators check variable output against sample inputs before publishing the agent.

**The built-in knowledge base tool is visible and directly invokable in the builder**

Administrators can view and explicitly invoke the built-in knowledge base tool directly within the Zoom Virtual Agent builder. Previously, this tool operated as an internal system component with no visibility or direct control in the builder interface. It now appears alongside other built-in tools, labeled as a system-provided tool, with a read-only name and an editable description. Administrators can invoke the tool multiple times across agent guidance or skills, making knowledge base lookup a deliberate, defined step in a workflow.

**Understanding Virtual Agent Skills**

Skills are the foundation of how a Virtual Agent executes tasks. Each Skill is defined by two core elements: a **trigger description** that specifies when the Skill should activate and a set of **instructions** that guide your Virtual Agent on how to complete the task. Instructions may include natural language guidance as well as references to Tools, which allow the Skill to interact with external APIs and systems.

**How the agent decides when to use Skills and Tools**

Once the trigger description matches a customer request, Zoom Virtual Agent evaluates all instructions within the Skill. The agent determines independently when to call a Tool based on the Tool’s name and description rather than explicit step-by-step directions. This means administrators must provide clear Skill instructions and Tool descriptions so that the agent can interpret them correctly. Importantly, the agent has access to all Skills and Tools, and can decide to use Tools associated with different Skills if they are relevant to the task.

**Dynamic Skill Loading reduces what each conversation has to carry**

For agents with multiple capabilities, Zoom Virtual Agent supports Dynamic Skill Loading. Instead of loading every Skill's instructions and Tools at the start of each conversation, the agent starts with a lightweight Skill index and loads only the Skills relevant to the current request. This reduces token usage, lowers response latency, improves Tool-selection accuracy, and makes prompt caching more effective, all while preserving full agent functionality.

**Best practices for designing Skills**

For reliable execution, administrators should write **clear, concise trigger descriptions** that accurately reflect when a Skill should activate. Instructions can be organized into multiple boxes for better Skill management; however, they are combined during execution. Administrators should avoid embedding explicit commands such as “call this Tool now” in instructions. Instead, instructions should describe the intended outcome, while Tool names and descriptions should signal their proper use. Limiting the number of Skills to around five (5) is recommended, as excessive configuration can lead to context window limitations.

**Saving and managing variables with Skills**

Skills themselves can't directly save data to global variables. Instead, administrators must combine instructions with the use of built-in or custom Tools. For example, a Skill may include instructions for collecting a customer’s account number, but the actual saving of that data to a variable must occur through a Tool such as **collect\_save\_response** or a custom integration. This separation is designed to support consistent and secure handling of sensitive data within the Zoom Virtual Agent framework.

**Example scenarios of Skill execution**

The interplay between Skills and Tools mirrors how a trained human agent applies their knowledge. For example, when a customer reports a lost credit card, Virtual Agent initiates the “Lost their credit card” Skill. The instructions require member verification, prompting the agent to use the “Verify the member” Skill before continuing. After verification, the agent returns to deactivate the card, offers to check recent transactions, and, if appropriate, transfers the caller to a live agent. Similarly, in a “Check recent transactions” scenario, an agent would first confirm the member's identity before retrieving transaction details. These scenarios illustrate how Skills provide structure, while the agent automatically selects Tools and sequences tasks to complete the work.

**Instructions can include clickable hyperlinks with custom label text**

Administrators can send clickable hyperlinks with customizable display text through the Instructions feature in Zoom Virtual Agent chat. Previously, URLs appeared as plain text with no way to define a label, which made it harder for end users to know where a link led. Now administrators can assign descriptive label text to any hyperlink, so users see clear context about the destination before they click. Clickable hyperlinks are supported across web chat, WhatsApp, desktop apps, mobile apps, and additional channels.

**An email tool can send email from within a Skill**

Account owners and administrators can add an email tool directly in the agent skill builder by typing a forward slash (/). The tool exposes configurable attributes — tool name, description, subject, body, sender address, receiver address, and a variable for storing the email. Both the subject and body accept static text, concatenated variables, and URLs, and all variables resolve to their actual values before the email is sent. The email tool is available across chat and voice deployments, including Zoom Contact Center and Zoom Phone.

**The email tool can run in any flow, including post-engagement steps**

Beyond the skill builder, the email tool is available as a step in any flow — conversational, curated, or transfer-to-live-agent — and in post-engagement actions that run after a session closes. This lets an agent send a summary or follow-up email at any point in a conversation, not only at hand-off. For example, an after-hours flow can email a case summary when no live agent is available. The recipient can be a collected session variable, such as the user's email from chat, or a static address, and the subject and body support both static text and variables, with multi-language support.

**Form and support channel setup are built into the agent workflow**

Form creation for voice agents is now part of the agent build workflow, so administrators no longer have to navigate away from the current tab to create one. Support channel creation for chat agents is embedded in the same build experience. The result is a consistent setup process across both agent types and fewer steps to configure and deploy a new use case.

**Custom Action runs LLM-driven logic and saves the result to a variable**

Custom Action is a built-in tool available when building Skills for chat agents. Administrators provide custom instructions that define the purpose and behavior of the tool's LLM execution, and the output saves to a variable — String, Numeric, JSON, or Array. This supports post-engagement tasks such as generating summaries, creating tags, or preparing notes to pass to CRM systems, ticketing platforms, or human agents.

{% hint style="info" %}
**Note**

This feature requires activation by Zoom. Contact your Zoom account team to enable this capability.
{% endhint %}

**A Skill library provides prebuilt, reusable Skills**

Administrators can browse a Skill library — a searchable catalog of prebuilt, reusable Skills that speeds up agent creation. Each library Skill combines one or more Tools with embedded instructions and guardrails tailored to common use cases such as appointment scheduling, case or lead creation, account lookups, and password resets. Administrators can add a Skill directly to an agent flow, edit it to create a new copy without changing the original, and save newly created Skills back to the library for reuse across agents.

{% hint style="info" %}
**Note**

This feature requires activation by Zoom. Contact your Zoom account team to enable this capability.
{% endhint %}

#### <mark style="color:blue;">Integrations connect to third-party services like CRM tools, e-commerce providers, or customer data platforms</mark>

Zoom Virtual Agent integrations connect voice and chat functionality to third-party services for additional chatbot functionality. Integrations let ZVA both push and pull data from third-party sources. For example, querying a customer’s data platform or e-commerce provider to retrieve the information needed to automate self-service while writing data back to those same systems. Integrations also connect ZVA to third-party CCaaS (Contact Center as a Service) vendors to help escalate conversations to a human agent when needed.

**Microsoft Teams integration for Zoom Virtual Agent campaigns**

The Microsoft Teams integration enables organizations to embed Zoom Virtual Agent campaigns directly inside Microsoft Teams as a native app. This brings agent chat capabilities into the Teams workspace, allowing internal helpdesk, HR, or IT support bots to serve employees directly within Teams channels or chats without switching between platforms. The integration supports both Teams desktop and web versions.

**WhatsApp and Facebook Messenger integration for Zoom Virtual Agent**

Zoom Virtual Agent chat agents can now be deployed on WhatsApp and Facebook Messenger through Zoom Contact Center, extending AI-powered support to more of customers' preferred messaging platforms.

Administrators configure this integration through the ZCC Flow Builder using the Bot Widget. Supported capabilities include:

* Text messaging
* Sending small media files
* Launching surveys
* Transferring to human agents

Currently unsupported features include:

* Large images and videos
* Curated carousels

{% hint style="info" %}
**Note**

This feature requires activation by Zoom. Contact your Zoom account team to enable this capability.
{% endhint %}

**Chat agents can connect to SMS and Zoom Chat messaging channels**

Zoom Virtual Agent and Zoom Contact Center administrators can connect chat agents to supported messaging channels, including SMS and Zoom Chat, through ZCC's existing messaging channel framework. This extends chat agent capabilities beyond the current web chat and social messaging integrations, allowing organizations to deliver consistent AI-powered support across additional customer-preferred channels.

**Okta integration enables self-service identity verification in voice and chat interactions**

The Okta connector integrates Okta's identity platform with Zoom Virtual Agent so both voice callers and chat users can recover accounts without agent intervention. The agent identifies the user and verifies identity through Okta Verify push notifications. After successful verification, it can trigger automated actions such as password resets, account unlocks, MFA factor resets, and Temporary Access Code (TAC) generation. Okta is designed to stay invisible to the end user throughout.

{% hint style="info" %}
**Note**

This feature requires activation by Zoom. Contact your Zoom account team to enable this capability.
{% endhint %}

**Ping Identity integration enables self-service identity verification in voice interactions**

The Ping Identity integration lets callers resolve common identity issues through self-service voice interactions. Supported actions include password recovery, account unlock, MFA factor reset, and factor enrollment. Zoom Virtual Agent can also trigger push or biometric verification requests and check the resulting status before it allows a protected action to proceed.

Ping Identity stays fully abstracted from the caller, and Zoom Virtual Agent never stores sensitive information such as passwords, one-time passcodes, or biometric data. If a verification attempt fails or an API request doesn't succeed, the agent falls back to offering a retry or an escalation to a live agent.

**FedEx connector enables shipment tracking self-service**

The FedEx connector brings logistics self-service into Zoom Virtual Agent through the FedEx Basic Integrated Visibility API. Customers can track any FedEx shipment — including Express, Ground, and SmartPost — using a tracking number, and the agent returns real-time status, current location, estimated delivery time, and full scan history. Customers can also subscribe, via an email address, to receive FedEx notifications for key events such as deliveries, exceptions, and updated delivery estimates. Those notifications are sent directly by FedEx to the recipient, so, based on current FedEx API behavior, no webhook infrastructure is required on your end.

**Custom script tools can authenticate through a third-party connector**

Administrators can select and import an existing third-party connector's authentication directly within the custom script tool to make authenticated API calls to any external endpoint. There's no need to store or manage credentials manually — security and credential handling stay governed by the third-party connector framework. This lets administrators extend integrations beyond the prebuilt connector options for more flexible, custom API interactions.

### Virtual Agent Behavior

The following section details next-generation Zoom Virtual Agent behavior during a conversation with an end user.

#### <mark style="color:blue;">Agent behavior in conversations pieces together structured prompts, Skills, Tools, and previous conversations</mark>

Zoom Virtual Agent is powered by third-party models that predict the next word in a sequence. To offer accurate, useful responses, the system combines a structured prompt with guidance, Skills, available Tools, and prior conversation history. Virtual Agents use this context to decide whether to respond directly, reference the knowledge base, or activate a Skill.

**How the agent chooses between Skills and an available knowledge base**

When a user asks a question, an agent evaluates whether the request aligns with a defined Skill or if it can be answered directly from the knowledge base. Skills are used when a query requires task execution or workflow steps, while the knowledge base is used when factual information is sufficient. The agent determines this choice automatically based on its instructions and available context.

Agent Guidance also influences Virtual Agents, especially in cases where certain topics are off-limits. A Virtual Agent isn't designed to perform agentic tasks such as looking for relevant Knowledge Base articles for any topics it’s been told, via guidance, to avoid. For more on Agent Guidance, see the previous section [Agent Guidance is an agent’s foundational identity, defining its tone, purpose and capabilities](#agent-guidance-is-an-agents-foundational-identity-defining-its-tone-purpose-and-capabilities).

**How Virtual Agent handles escalations and handoffs**

Zoom Virtual Agent includes an escalation threshold control that determines how many times a user must request a human agent before the system transfers the conversation. This setting allows an agent additional opportunities to resolve customer inquiries before routing to live support.

Previously, any user message requesting a live agent would immediately trigger an escalation. With this update, administrators can configure a retry count in the chat agent settings that requires users to request human help multiple times before the transfer occurs. During these interim requests, a Virtual Agent prompts the user to restate their question, giving the AI additional context to attempt resolution. The system tracks each escalation request, and once the count reaches the configured threshold, the chat routes to a human support channel.

The default value is **1**, which preserves the previous behavior where the first request transfers immediately. Setting a higher threshold allows an agent to make additional resolution attempts before handing off the conversation. This approach can improve containment and deflection metrics by reducing unnecessary handovers and increasing automation rates. The escalation threshold aligns with the existing threshold feature available for voice agents, providing consistent behavior across channels.

**Transfer and end conversation tools control what consumers experience at handoff and close**

Administrators can create multiple instances of the built-in transfer tool, assigning each one its own name, transfer destination, and pre-transfer message. That way, the message a consumer receives before moving to a human agent, department, queue, or other designated destination can match the scenario that triggered the transfer. Each instance also supports a default message that applies when no destination-specific message has been defined.

The built-in end conversation tool supports custom closing messages that replace the default goodbye. Administrators can define separate messages for chat and voice, and for inbound and outbound conversations. If the agent has already delivered a closing message in a preceding turn, administrators can configure a silent ending so the consumer doesn't receive a duplicate or conflicting farewell. When no custom message is configured, Zoom Virtual Agent uses the default message.

The end conversation tool is also available directly in curated flows for chat and voice, so administrators can end a conversation at any defined point in the flow logic. To deliver a closing message first, place a Send Media widget ahead of the end conversation tool. This removes the need to call a separate skill only to end a conversation.

**Escalation-by-design provides a standardized framework for handoff analytics**

Zoom Virtual Agent analytics includes a standardized escalation-by-design framework across both chat and voice. This framework lets administrators define business conditions that classify certain escalations to a human agent as "by design,” resulting in intentional transfers.

To configure this feature, administrators must enable "Additional conditions for 'escalated by design'" in AI Studio. Once enabled, the system auto-detects design escalations upon publication. Administrators can include language in their agent guidance and skill instruction that the “escalation is by design” which will then be used by this feature to determine the conditions for when an escalation is by design.

**How the system prompt shapes behavior**

Each interaction is guided by a system prompt, which includes the current date, user identity, agent instructions, language preferences, available APIs, tool descriptions, conversation history, and the user’s latest request. Administrators directly influence agent behavior through the **agent instructions** and the **tools they configure**, while the system manages all other fields. This structured context provides Virtual Agents with the right information to produce consistent, relevant answers.

**Flow of a typical conversation**

A typical interaction follows this predictable pattern:

{% stepper %}
{% step %}
The user submits a request.
{% endstep %}

{% step %}
The agent reviews its guidance, Skills, Tools, and Knowledge Base content.
{% endstep %}

{% step %}
The agent “thinks” through available options, identifying what information is missing and whether a Skill, Tool, or API call is required.
{% endstep %}

{% step %}
The agent either makes the call (if needed) or provides a direct response.
{% endstep %}

{% step %}
If the knowledge base returns multi-step instructions, the agent delivers only the first step, confirms user progress, and then proceeds sequentially.
{% endstep %}
{% endstepper %}

**Dial-by-name routing for Zoom Phone**

Zoom Virtual Agent now supports dial-by-name (also called transfer-by-name) routing for Zoom Phone. When deployed in a voice workflow, the agent can collect a spoken or typed name, interpret the request, and route the call to the correct user or extension. This enhancement enables more natural voice-driven navigation and reduces manual keypad entry. Administrators can configure dial-by-name routing rules in the Zoom Phone settings to determine which users or departments are eligible for automated routing.

**Standalone Dial-by-Name directory**

For Receptionist standalone voice deployments, administrators can create and manage a local contact directory within the Transfer-by-Name tool to support name-based call transfer. Each entry holds a contact name and an external phone number. When a caller asks to be connected to a person or department, the voice agent matches the request against the directory and transfers to the associated number. Entries can be added individually or imported in bulk from a CSV, and the imported list can either append to or replace existing entries with similar names, and can be exported. Changes take effect without rebuilding the full voice agent.

The standalone directory is built for ZVA standalone deployments where the customer doesn't have a Zoom Phone directory to look up. Zoom Phone customers can also use the Transfer-by-Name tool, but because only one copy of the tool is supported per agent, they choose whether the tool draws on their own (customer) directory or the Zoom Phone directory. The two are alternatives selected per agent, not layered together.

**Extended maximum engagement duration for inactive conversations**

Administrators can set the **Auto-close inactive engagements within flows** timer to a maximum of 24 hours, up from the previous 12-hour limit. The admin interface displays engagement duration in a clear hours-and-minutes format, which aligns Zoom Contact Center engagement duration limits with Zoom Virtual Agent and helps reduce configuration errors by removing the need for manual minute calculations.

**Call summary and variable integration with Zoom Phone**

Zoom Virtual Agent can transfer conversation summaries and custom metadata to Zoom Phone agents during call handoffs through variable pass-through. Administrators use the ZVA admin portal to choose which variables display in the Zoom Phone interface during transferred calls. This gives agents pre-collected caller information without asking again, and can help shorten average handle times.

Zoom Phone users can see ZVA-generated call summaries and key variables in three moments:

* Before answering a call
* During the conversation
* After the call ends

Passing variables requires a Zoom Phone Customer Engagement Pack license (formerly known as the Zoom Phone Power Pack). Call summaries don’t require this license.

{% hint style="info" %}
**Note**

This feature requires activation by Zoom. Contact your Zoom account team to enable this capability.
{% endhint %}

**Best practices for optimizing agent behavior**

Administrators should design Skills so that each set of instructions is clear and independent, reducing overlap or conflicts. Skill ordering can affect how the agent prioritizes actions, so descriptions should be written to minimize ambiguity. When combined with well-structured knowledge base content, these practices help the agent smoothly determine when to respond directly, when to reference documentation, and when to execute a workflow.

For more information, see our Technical Library articles [Customize User Chat Support Experience](https://library.zoom.com/business-services/zoom-contact-center/expert-insights/customize-user-chat-support-experience) and [Integrate Zoom Contact Center Features Into Your Website](https://library.zoom.com/business-services/zoom-contact-center/expert-insights/integrate-zoom-contact-center-features-into-your-website).

**Virtual Agent refines its reasoning through structured self-improvement**

Zoom Virtual Agent uses a structured self-improvement framework that refines how the agent reasons through tasks and follows enterprise policies. This is automatic and doesn’t require admin configuration.

The system converts enterprise policies and procedures into structured, step-by-step decision protocols. This helps Virtual Agent follow verifiable logic paths rather than relying on implicit inference.

Self-improvement actions include:

* Generating test scenarios
* Evaluating agent responses against expected outcomes
* Identifying reasoning gaps
* Updating decision protocols

Administrators don’t interact with the self-improvement system directly. The agent becomes more consistent, policy-compliant, and accurate over time without manual retraining. Improvement is observable through Virtual Agent performance and analytics and Agent Tracing. See the [Analytics and Reporting](https://library.zoom.com/business-services/zoom-virtual-agent/zoom-virtual-agent-analytics-reporting.md) section for more information.

**Virtual Agent can start automated outbound calls to customer lists**

Administrators can configure Zoom Virtual Agent to place outbound calls to customer lists based on defined business rules and scheduling parameters. A Virtual Agent can start calls, deliver scripted messages, answer customer questions using its knowledge bases and skills, and escalate to live agents when needed. Built-in call management controls help align outreach with customer preferences.

Administrators create outbound campaigns within AI Studio by selecting a contact list, assigning a virtual voice agent, defining a caller ID, scheduling dialing windows, and configuring retry behavior.

Outbound calling leverages Zoom Contact Center's outbound campaign infrastructure, and engagement results and call status are recorded in ZVA analytics. Outbound calling is currently available for voice-only channels.

**Preview dialer mode**

ZVA outbound now uses preview dialer mode in place of the previous agentless dialer mode. Previously, the outbound call was placed first and the bot voice-flow session was only spun up after pickup, so the callee could hear a stretch of dead air before the bot spoke. Now the bot session is initialized and held in a silent, ready state before the call is placed. The moment the call bridges, the bot is already listening and responds immediately — removing the pause callees used to hear on pickup and making outbound calls feel like a real conversation from the first hello.

**Zoom Phone customers can use SMS capabilities within Zoom Virtual Agent**

Zoom Virtual Agent and Zoom Phone customers can use Zoom Phone SMS capabilities directly within Zoom Virtual Agent to enhance voice interactions. During a call, a Virtual Agent can send customizable SMS messages containing dynamic text, URLs, or survey links. The system supports variables and splits longer messages for efficient delivery. This allows customers to receive detailed information that's difficult to convey by voice alone.

To use this feature, the following prerequisites must be met:

* Assign a valid number to the Auto Receptionist (AR)
* Enable the SMS policy
* Add at least one AR member to the SMS/Allowed Member List

{% hint style="info" %}
**Note**

This feature requires activation by Zoom. Contact your Zoom account team to enable this capability.
{% endhint %}

**A Business Hours tool enables conditional routing and messaging based on schedules**

Administrators can configure a Business Hours tool that enables customized greetings, instructions, and routing rules based on business hours and holiday schedules. The tool supports custom time zones, business hours, and holiday configurations with options for recurring schedules. Each Business Hours tool can be referenced in Skills to create conditional logic.

For example, it can route calls to live agents during open hours or display closure messages during off-hours. The tool applies to both inbound and outbound scenarios.

{% hint style="info" %}
**Note**

This feature requires activation by Zoom. Contact your Zoom account team to enable this capability.
{% endhint %}

#### <mark style="color:blue;">Multi-instance deployment for multiple locations and departments</mark>

The Zoom Virtual Agent multi-instance platform with Zoom Phone delivers scalable, personalized voice experiences across many locations or departments. Organizations manage brand-level configurations centrally while allowing store- or branch-specific customization for greetings, knowledge bases, and skills. By using Zoom Phone's routing data, Zoom Virtual Agent determines the correct department or store extension automatically, which removes the need to set up per-store routing by hand. Hierarchical role management, version control, and selective publishing simplify administration, speed up deployment, and keep the customer experience consistent across all sites.

**Note:** Instance and instance-group filters let administrators scope engagements to a single instance (for example, one store location) or an instance group (for example, a regional group of stores), alongside the existing virtual agent and version filters. These filters apply across the Overview, Virtual Agent Performance, and Conversation Details reports.

{% hint style="info" %}
**Note**

This feature requires activation by Zoom. Contact your Zoom account team to enable this capability.
{% endhint %}

#### <mark style="color:blue;">Zoom Virtual Agent supports multiple languages and dialects</mark>

The next-generation Zoom Virtual Agent supports multiple languages and dialects across chat and voice. The list of currently supported languages includes:

| <p>Arabic<br>Arabic (Gulf)<br>Cantonese<br>Catalan<br>Chinese (Simplified)<br>Chinese (Traditional)<br>Danish<br>Dutch (Netherlands)<br>English (Australia)<br>English (Indian)<br>English (Italian)<br>English (New Zealand)<br>English (Scottish)<br>English (Singaporean)<br>English (UK)</p> | <p>English (US)<br>French (France)<br>French (Canada)<br>Finnish<br>German<br>English (Welsh)<br>Hebrew<br>Hindi<br>Indonesian<br>Italian<br>Japanese<br>Korean<br>Norwegian<br>Malay<br></p> | <p>Polish<br>Portuguese (Portugal)<br>Portuguese (Brazil)<br>Romanian<br>Russian (Russia)<br>Spanish (European)<br>Spanish (Mexico)<br>Spanish (US)<br>Swedish<br>Thai<br>Turkish<br>Vietnamese<br><br><br></p> |
| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

The system displays available voice actors specific to the selected language and supports localized text-to-speech capabilities for numbers, dates, phone numbers, and other formatted content. This expansion enables organizations to provide more localized customer experiences across multiple regions.

{% hint style="info" %}
**Note**

Additional languages will be added over time. This document will be updated as new language support launches. Adding new languages requires activation by Zoom. Contact your Zoom account team to enable additional language capabilities.
{% endhint %}

**Expanded multi-language support for chat agents**

Zoom Virtual Agent chat experiences now support an expanded set of languages, allowing administrators to configure a single chat agent that serves customers across multiple regions and languages. This enhancement eliminates the need to create and maintain separate agents for each supported language, returning to the streamlined multilingual approach that was available in ZVA 1.0.

When creating a chat agent, administrators can select multiple languages that the agent will support. Once configured, the system automatically determines the engagement language based on factors such as welcome screen selections, browser HTML language settings, and other contextual signals. The selected language remains consistent throughout the conversation, providing a coherent experience for the end user.

Machine translation handles the localization of greeting messages, flow content, and button text automatically. This means administrators don't need to translate each element of the chat experience when adding language support.

The current release focuses on language selection at the start of the conversation. Administrators configure supported languages during chat agent creation, and the system locks in the engagement language when the conversation begins.

#### <mark style="color:blue;">Zoom Virtual Agent is not available to Zoom for Government customers</mark>

Zoom Virtual Agent is not available to Zoom for Government (FedRAMP) customers at this time.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://library.zoom.com/business-services/zoom-virtual-agent/zoom-virtual-agent-admin-experience.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
