Robert Helewka
e88449d15a
studies/202512_GenesysCX -> studies/202512_TEI_Genesys_CX_Cloud, rebuilt as pattern Variant 4 (TEI composite reproduction): - teicalc/ self-contained engine: Forrester's tables as the never-edited verbatim anchor (incl. the p.14 typo note and the $0 AI-token line), generic model/scenarios/staging carried over from the Amazon Connect study, ClientDrivers overlay (agents / weekly interactions / revenue, flat composite so no growth re-base) with ai_tokens_annual as a direct input for the token line the published study models at $0 - one deliverable notebook (business_case.ipynb): widget-pair sidebar drivers incl. the AI-token price, published-vs-overlay KPI columns, cash-flow/waterfall/scenario charts, verification gate, backstage JSON data appendix - gate + tests reproduce the published totals within $2: NPV $10.8M / ROI 266% (engine $10,783,466 / 265.79%; payback 3.3 months, not headlined in the PDF); 29 study tests, headless nbconvert green, stage simulation leak-free, exports carry the appendix - old Athena workflow (00_provision..04_export, config.py, seed_data.py, PALLADIUM_GENESYSCX_* keys, ATHENA_EXPECTED reconciliation) deleted; git history preserves it With the last legacy study migrated, the retirement lands too: - app/ (Streamlit UI) and core/notebook_helpers deleted; nothing else imported them - streamlit stripped from pyproject extras, requirements.txt, Makefile; .env.example reduced to the Athena keys; 00_setup.ipynb and core/bootstrap.py repointed at the pattern studies - root README reworked: self-contained studies + slim core/ Athena toolkit (tei_client, calculations, export, cli) All suites green: Genesys 29, Amazon Connect 27, CTM 55, template 7, root 58. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
4.1 KiB
Genesys Cloud AI Experience metering details
2026-06-07 https://help.genesys.cloud/articles/genesys-cloud-tokens-model/ This table describes the Genesys Cloud AI product’s raw meter and how many tokens are consumed. Note: Direct Messaging (DM) channels include inbound and outbound messages. Social Responses messages include outbound messages only.
Genesys Cloud product Units per token Bots (Voice) 17 minutes per token. For more information, see the AI section of the Genesys Cloud pricing hub. Bots (Digital) 51 sessions per token. For more information, see the AI section of the Genesys Cloud pricing hub. Virtual Agent 0.5 tokens per Virtual Agent interaction - An interaction is defined in accordance with existing Genesys Cloud token-based pricing. Agentic Virtual Agent 1.2 tokens per interaction - An interaction is defined in accordance with existing Genesys Cloud token-based pricing. Agent Copilot [concurrent] One user requires 60 tokens Agent Copilot [named] One user requires 40 tokens AI Scoring 20 evaluations scored with AI scoring per token AI Translate Two translations per token AI Summary and Insights 50 AI summaries/insights per token. However, if you enable Agent Copilot simultaneously, then Supervisor Copilot summaries and insights do not consume tokens and instead rely on Agent Copilot functionality. Apple Messages for Business 400 inbound or outbound messages per token. Facebook Messenger† 400 inbound or outbound messages per token. Instagram Direct Messaging† 400 inbound or outbound messages per token. WhatsApp Messaging† 400 inbound or outbound messages per token.
Other charges apply for WhatsApp. For more information, see the Messaging section of the Genesys Cloud pricing hub.
X (formerly Twitter) Direct Messaging 400 inbound or outbound messages per token.
Other charges apply for X integrations. For more information, see the Messaging section of the Genesys Cloud pricing hub.
Genesys Cloud Social 400 social post ingestions per channel per token. For more information, see the Messaging section of the Genesys Cloud pricing hub.
Social Post Responses 400 outbound messages per channel per token.
Predictive Engagement No charge for token usage. For more information, see Can I use digital user tracking at no additional cost? and Predictive Engagement and digital user tracking. Predictive routing 17 routes per token. One token is consumed for every 17 interactions routed with predictive routing. For more information, see Predictive routing overview. Speech and Text Analytics [named] One user requires 30 tokens Speech and Text Analytics [concurrent] One user requires 45 tokens Genesys Cloud Copilot 20 AI actions per token, no charge for Genesys Cloud knowledge queries. For more information, see Genesys Cloud Copilot AI actions overview.
† For Facebook, Instagram, and WhatsApp: If the organization has not moved to the Genesys Cloud AI Experience token pricing, then legacy, conversation-based pricing applies. Other charges apply for X integrations. For more information, see Messaging in the Genesys Cloud pricing hub.
Virtual Agent interactions explained
A single interaction is contained by a single billingID. A billingID represents a single interaction on any channel of any length. A single interaction is delimited by end interaction events. A single billingID can contain multiple end interaction events.
The following actions trigger end interaction events:
Exit action in flow (return calling flow) Disconnect action in the flow Disconnect when the participant hangs up the phone Disconnect via a Transfer to ACD action Exit or disconnect handling for an unexpected error Exit or disconnect handing for a recognition failure (continuous no matches or no inputs) Exit or disconnect handling for Max No Input override (if set, overrides recognition failure settings) Exit handling for agent escalation Digital expiry after inactivity (72-hour async timeout) When Genesys Cloud transfers interactions between inbound flows and Virtual Agent flows, the same billingID remains. When an action triggers an end interaction event and transfers no longer occur, then Genesys Cloud closes the billingID.