Source record · tier 2 current vendor documentation

Use AI agents for customer interactions

Publisher: Cisco Systems, Inc. (Webex Help Center)
URL: https://help.webex.com/en-us/article/s0qro1/Use-AI-agents-for-customer-interactions
Published: 2026-08-25
Updated: unknown
Accessed: 2026-09-04
HTTP status: 200
License: Cisco proprietary documentation, all rights reserved; no-redistribution; short excerpts and locators only

Source notes citing this source

Cisco states that access to the autonomous AI agent for voice calls is currently limited to specific customers and directs a reader who wants it to Cisco support. in context
An Enable voice recording check box in the Virtual Agent V2 advanced settings allows recording of the conversation between the AI agent and the customer, and Cisco states that those recordings appear on the Sessions page within the AI Agent Studio application. in context
Cisco states that custom events, the mechanism by which a flow orchestrates fulfilment actions such as retrieving data from external systems or calling third-party APIs during an AI agent conversation, are currently supported for scripted and autonomous AI agents through the voice channel only. in context
On an escalated outcome the Virtual Agent V2 MetaData variable carries an escalation_type of custom or system and an escalation_trigger naming what caused it, where a custom escalation names the transfer action configured on the agent and a system escalation carries the trigger agent_transfer. in context
The default input language and output voice configured on a Webex AI Agent are overridden from the flow by Set Variable activities placed before the Virtual Agent V2 activity that set Global_Language to a language code and Global_VoiceName to a voice name code, and Cisco warns that a voice not supported by the engine the AI agent uses sends the call down the activity's error path. in context
The Language drop-down on the Webex Connect AI Agent node is populated from the languages configured in the AI agent's own settings and is disabled for an agent configured with a single language. in context
The Webex Connect AI Agent node offers 2 methods, Process Message which sends a user message to the selected agent and returns its response, and Close session which ends an AI agent session, and Cisco states that a session inactive for a specified period is closed automatically to optimise resources without naming that period. in context
Cisco states that the service applies automated detection of patterns that may indicate payment card industry data in AI Agent recordings and limits its visibility in AI Agent Studio, and that the automated detection may not identify every instance, naming 3 scenarios: unprompted disclosure by the caller outside the expected call flow, speech-to-text transcription of card details that is incomplete inaccurate or in an unexpected format, and a call disconnected before backend systems can fully analyse the conversation. in context
Cisco states that the Webex Connect and Webex Contact Center integration currently supports 6 digital channels for AI agents: WhatsApp, SMS, Email, Facebook Messenger, Apple Messages for Business and Live Chat. in context
Cisco's published example of the default Webex Contact Center system transfer output carries a spoken message telling the caller they will be connected with a human representative and asked to hold while the transfer happens, delivered as the input to the agent_transfer action. in context
The Virtual Agent V2 activity has 3 output paths: Handled when the virtual agent execution completes, Escalated when the call must be escalated to a human agent, and Errored which the flow takes in any error scenario. in context
The Virtual Agent V2 activity returns 3 output variables to the flow: TranscriptURL pointing at the transcript of the conversation, MetaData carrying the JSON the agent returns as part of fulfilment custom event handling or a transfer action, and StateEventName carrying the name of the custom event received after the system triggers one. in context
Webex Contact Center exposes 2 kinds of AI agent to a voice flow through the same Virtual Agent V2 activity, selected by the Contact Center AI Config value: Webex AI Agent Scripted and Webex AI Agent Autonomous, each then offering its own list of published agents. in context
Access to the autonomous AI agent for voice calls is currently limited to specific customers, on both the cloud and the Contact Center Enterprise product lines, and requires contacting Cisco support. in context
In cloud Webex Contact Center the integration point is the Virtual Agent V2 activity in Flow Designer, where a Contact Center AI Config selector offers Webex AI Agent Scripted or Webex AI Agent Autonomous and the flow author then chooses a published agent. in context
On digital channels the AI Agent node in the Webex Connect flow builder exposes error outcomes (onError, onInvalidCustomerID, onInvalidMessage), success outcomes (onSuccess, onAgentHandover) and a timeout outcome, onTimeOut, which fires when the agent has not responded within 15 seconds. in context
Webex Connect and Webex Contact Center integration currently supports 6 channels for AI agents: WhatsApp, SMS, Email, Facebook Messenger, Apple Messages for Business and Live Chat. in context
The Virtual Agent V2 activity exposes 3 flow outcomes: Handled when the virtual agent completes execution, Escalated when the call must go to a human agent, and Errored for any error scenario. in context
Digital channels use the AI Agent node in Webex Connect rather than Virtual Agent V2, and the node's success outcomes include onAgentHandover. in context
In the Virtual Agent V2 activity, the administrator selects Webex AI Agent Scripted or Webex AI Agent Autonomous and then picks a published agent from the Virtual Agent list. in context
If language and voice overrides are not set on the Virtual Agent V2 activity, it takes the input language and output voice from the Global_Language and Global_VoiceName variables. in context
VirtualAgentV2.MetaData returns JSON that includes fulfillment actions, the escalation type and transfer triggers, and VirtualAgentV2.TranscriptURL stores a URL to the conversation transcript. in context
The Virtual Agent V2 activity has Handled, Escalated and Errored output paths, for a completed self-service interaction, a required escalation to a human agent, and an error. in context
On voice, the Virtual Agent V2 activity's State Event settings (event name and event data) send custom events to the AI agent, and VirtualAgentV2.StateEventName holds a custom event name received from the agent. in context
Webex AI agents built in AI Agent Studio reach voice calls through the Virtual Agent V2 activity in Flow Designer. Digital channels use the AI Agent node in Webex Connect flows instead. in context
Cisco states that autonomous AI agents on the voice channel are currently limited to specific customers. in context
On digital channels the Webex Connect AI Agent node signals a request for a human with an onAgentHandover outcome, rather than the voice activity's Escalated outcome. in context
The output variable VirtualAgentV2.MetaData stores the JSON data that the system receives from the agent as part of fulfillment, custom-event handling or a transfer action, and can drive later flow logic. in context
For Webex AI agents, the voice set through Global_VoiceName must be supported by the engine that the AI agent uses. in context

Cite this source record

APA

WarmTransfer. (2026, August 25). Use AI agents for customer interactions. WarmTransfer. https://warmtransfer.net/knowledge/sources/cisco-help-s0qro1-wxcc-use-ai-agents

BibTeX

@misc{warmtransfer-cisco-help-s0qro1-wxcc-use-ai-agents,
  title  = {Use AI agents for customer interactions},
  author = {{WarmTransfer}},
  year   = {2026},
  url    = {https://warmtransfer.net/knowledge/sources/cisco-help-s0qro1-wxcc-use-ai-agents},
  note   = {Cisco Systems, Inc. (Webex Help Center), accessed 2026-09-04}
}