Contact Center: Agent Burnout Detection - AI Transparency Technical Note

Publisher

Cisco Systems, Inc. (Cisco Trust Portal)

URL

https://trustportal.cisco.com/c/dam/r/ctp/docs/white-paper/collaboration/ai-transparency-agent-burnout-detection-technical-note.pdf

Published

2025-01-22

Updated

unknown

Accessed

2026-09-05

HTTP status

200

License

Cisco proprietary documentation, all rights reserved; no-redistribution; short excerpts and locators only

Claims citing this source

• The Agent Burnout Detection note closes by saying its scores represent an approximation of the actual customer satisfaction although the feature measures agent burnout and the note never says what the burnout index approximates. fact in context
• The Agent Burnout Detection technical note states that the model's outputs should not be used for assessing agent performance having performance appraisal discussions penalizing or compensating agents or informing decisions on an agent's employment and right to work. fact in context
• The Auto CSAT and Agent Burnout Detection restrictions differ in 2 ways: Auto CSAT qualifies its prohibition with the words in isolation and Agent Burnout Detection does not while Agent Burnout Detection adds performance appraisal discussions which Auto CSAT does not name. disputed in context
• The Trust Portal record for the Agent Burnout Detection transparency note carries a document expiry date of 22 January 2026, which had already passed at the access date of 5 September 2026, while the record remained marked Active and latest version. fact in context
• The Agent Burnout Detection and Auto CSAT models are stated to be proprietary and not publicly available, usable by Cisco only within Webex applications or with Webex software development kits. fact in context
• Cisco states it is not aware of any known biases associated with the Agent Burnout Detection model while committing to routine monitoring and rebalancing of the training dataset for user-identified behaviours. fact in context
• Cisco states that customer content is used exclusively to customise the Agent Burnout Detection model for that customer's own organisation and is not used to develop or improve the general model or any other customer's model. fact in context
• The Agent Burnout Detection model is Cisco's own algorithm based on agent behaviour and performance metrics; the note names no third-party model or vendor anywhere. fact in context
• Cisco states that Agent Burnout Detection output should not be used for performance appraisal, for penalising or compensating agents, or for decisions on an agent's employment and right to work. fact in context
• Agent Burnout Detection outputs a burnout index on a continuous scale from 0 for no burnout to 1 for high burnout, together with recommended corrective measures. fact in context
• The Agent Burnout Detection model learns from a rolling 90 days of data once every 30 days, programmatically and with no human involvement in that cycle. fact in context

Cite this source record

APA

WarmTransfer. (2025, January 22). Contact Center: Agent Burnout Detection - AI Transparency Technical Note. WarmTransfer. https://warmtransfer.net/knowledge/sources/cisco-trustportal-tn-wxcc-agent-burnout

BibTeX

@misc{warmtransfer-cisco-trustportal-tn-wxcc-agent-burnout,
  title  = {Contact Center: Agent Burnout Detection - AI Transparency Technical Note},
  author = {{WarmTransfer}},
  year   = {2025},
  url    = {https://warmtransfer.net/knowledge/sources/cisco-trustportal-tn-wxcc-agent-burnout},
  note   = {Cisco Systems, Inc. (Cisco Trust Portal), accessed 2026-09-05}
}