Genesys Cloud AI experience

Genesys Cloud AI overview provides artificial intelligence capabilities on the Genesys Cloud platform to automate tasks, meet business needs, and elevate customer and employee experiences. Key features include real-time data collection and analysis to uncover patterns and predict behaviors, security by design with strict ethics and data standards, regulatory compliance for global deployment, contextual intelligence across all interactions, and quick implementation for rapid time to value. Genesys Cloud helps differentiate customer experiences and drive workforce efficiency with AI-powered capabilities.

Genesys Cloud implements a comprehensive token-based pricing model for AI features across CX 1-4 license tiers, enabling organizations to access diverse artificial intelligence capabilities including Agent Copilot, AI Scoring, Translation, Virtual Agent services, predictive routing, analytics, and messaging channels. Named users receive monthly allocations of 250 tokens, while concurrent users receive 350 tokens, with tokens renewing monthly without carryover. Token consumption rates vary by feature and usage type. Voice bots consume 1 token per 17 minutes of operation, while digital bots consume 1 token per 51 sessions. Virtual Agent sessions require 2 tokens per session, with Agentic Virtual Agent consuming 1 token per session (increasing to 1.2 tokens on May 14, 2026). Agent Copilot requires 60 tokens for concurrent users or 40 tokens for named users. Speech and Text Analytics require 45 tokens for concurrent users or 30 tokens for named users. AI Scoring provides 20 evaluations per token, AI Translate offers 2 translations per token, and AI and Insights deliver 50 summaries per token. Messaging channels including Apple Messages for Business, Facebook Messenger, Instagram Direct Messaging, WhatsApp, and X Direct Messaging each consume 400 inbound or outbound messages per token. Predictive Routing consumes 1 token per 17 routed interactions, while Genesys Cloud Copilot provides 20 AI actions per token. When interactions utilize multiple AI resources, billing charges are based on the highest-tier resource consumed. Virtual Agent sessions are defined by billing IDs and terminate through flow exits, disconnections, transfers, timeouts, or agent escalations. Token pricing varies by currency, ranging from USD 1.00 to JPY 120. New customers receive default access to Genesys Cloud AI and AI Experience tokens, while existing customers can order tokens through AppFoundry or their Genesys representative. Deprecated AI Experience Bundles will be removed upon renewal, with customers seeking earlier migration directed to contact their representative

Genesys Cloud implements a comprehensive fair use policy across multiple product features and license tiers (Communicate, CX 1-4, and EX) that allocates resources based on billable users and license types to manage consumption-based pricing and control costs. The policy applies to core features including BYOC Cloud (1,000-6,500 minutes per user at $0.00120 per minute overage), data storage (17.5-55.25 GB per billable agent at $0.25/GB overage), basic routing/IVR (500-5,525 APIs at approximately $0.01 per minute overage), API on-demand (10,000-234,000 calls monthly at $0.0001 per request overage), voice transcription in Native, Extended, and Legacy variants (100-3,900 minutes at $0.01 per minute overage), BYO SMS messaging (300-700 messages per user at $0.002 per message overage), workitems (1,800 items per user monthly at $0.04 per overage item), Journey Management events (20,000-26,000 per user at $0.0010 per event overage), AI Experience tokens, and outbound dialing campaigns (call attempts tracked with $0.005 per call overage). Fair use allocations are calculated by multiplying the number of billable users by the per-user allowance for each license tier and license type (Named, Concurrent, Hourly Interacting, and Hourly Logged In). Allocations are determined based on the greater of committed or actual monthly usage, with base license tier and add-on allocations summed together; however, allocations remain non-stackable when overlapping between base licenses and add-ons, meaning only the higher allocation applies. Monthly allocations are pooled across all users in an organization, with usage tracked through the Billing & Usage page. Unused minutes or requests do not roll over to subsequent months. Specific feature policies include BYOC Cloud charges applied exclusively to BYOC Cloud solutions with no additional Edge charges, data storage calculations that exclude archived items, user ad hoc recordings, Collaborate chats, voicemails, and transcripts of policy-based calls, and basic routing/IVR session timers that measure flow duration from initiation to completion while excluding in-queue call flows. Voice transcription services transcribe voice interactions from external and internal channels as well as voicemails, providing confidence scores, timestamps, and participant information; legacy voice transcription offerings cannot be ordered as of August 26, 2025, though existing customers may maintain coexisting Native and Extended variants through August 26, 2025. SMS messages exceeding character limits (160 for GSM, 70 for Unicode) are segmented for delivery with each segment counted separately, while MMS messages count individual images separately. Work Automation licensed customers retain workitem fair use allocations through contract expiration, with consumption-based pricing applied to legacy workitem support for existing customers. Outbound dialing campaign call attempts include all dialing outcomes except invalid phone numbers, time zone restrictions, or policy-based skips, with fair use limits enforced beginning July 20, 2026, or as specified in individual contracts. Organizations exceeding their monthly allocations incur overage charges billed at rates varying by currency (USD, CAD, AUD, NZD, GBP, EUR, BRL, JPY, ZAR), with overage charges appearing on invoices as specific line items. Committed overage tiers may be negotiated with account teams to reduce per-unit rates based on defined usage commitments. Usage calculations are tracked through the Billing & Usage page, with tools available to monitor actual consumption and adjust retention policies accordingly. The policy applies across all applicable add-ons (Digital, WEM, Agent Assist, Work Automation, Agent Copilot, Journey Management, Speech and Text Analytics, and Outbound dialing campaigns) and was consolidated and updated as of November 7, 2023, with subsequent revisions in June 2023, September 2024, and February 17, 2025.

Genesys Cloud Agent Copilot integrates artificial intelligence and Large Language Models to enhance agent productivity and customer service delivery throughout the contact lifecycle. The platform automates after-call work through intelligent wrap-up code suggestions, conversation summaries, and resolution tracking, while simultaneously providing real-time next-best-action recommendations and customer intent determination during live interactions. The system encompasses a comprehensive technical architecture featuring natural language understanding configuration, AI model and LLM input management, and token-based pricing for AI processing functions. Interaction summaries are retained beyond 10 days for extended reference purposes. Administrative capabilities include performance analytics dashboards, rule configuration for agent assistance, and role-based access controls that enable granular permission management across the organization. Agent-facing features include interactive AI agents, personalized conversation summaries, customizable AI Guides built through AI Studio integration, agent checklists developed from business instructions, transfer summaries, and knowledge article management with segment filtering. The platform provides answer highlighting functionality, help options for troubleshooting, and knowledge workbench integration to support agents during customer interactions. Related Copilot features such as intent miner are also supported. The implementation framework addresses setup prerequisites, configuration requirements, and operational guidance. Multi-language support enables deployment across diverse environments, while queue management configuration allows customization for specific organizational needs. The system provides transparency regarding persistence and generation failures, supporting troubleshooting and optimization efforts. Comprehensive documentation covers initial deployment best practices, natural language understanding optimization, and operational questions regarding persistence, wrap-up code accuracy, knowledge article filtering, and interaction detail visibility. Support resources are available through community forums, enabling organizations to maximize the value of Genesys Cloud Agent Copilot while reducing administrative burden on agents

Genesys Cloud's AI Studio is a centralized workbench that enables organizations to build, manage, and deploy AI-powered customer experiences with comprehensive governance and scalability. The platform supports creation of agentic virtual agents capable of reasoning between actions and knowledge for action-oriented interactions, AI Guides that convert business instructions into Virtual Agents through AI prompts, and customizable conversation summaries for agents. Key capabilities include guide creation and publishing, virtual agent preview and deployment, integration with Architect Virtual Agent flows, AI Studio APIs, and permission management tools. The system implements robust governance controls throughout the entire AI lifecycle, with administrators benefiting from a unified environment featuring built-in oversight mechanisms. Genesys Cloud offers configurable summarization capabilities designed for both novice and experienced users, with options ranging from standard summaries for less experienced users to advanced summaries for experienced prompt writers. Users can leverage either the native Genesys large language model engine or integrate third-party LLM summarization services through the Genesys Summarization Connector. Implementation involves installing and configuring the Genesys Summarization Connector, adding external summarization sources to AI Studio, and assigning configurations to Agent Copilot. Feature consumption and costs are managed through Genesys Cloud AI Experience tokens under a token-based pricing model, enabling administrators with visibility into system usage patterns and organizations to monitor and control usage of summarization and other AI capabilities. Agentic virtual agents are noted as a feature coming soon, indicating continued platform expansion

Genesys Cloud provides advanced conversational bots powered by Genesys AI that handle customers like human agents, increasing deflection rates. The Virtual Agent creates personalized self-service interactions using knowledge bases, predefined articles that respond to customer queries. Knowledge authors manage articles, refine search, and view performance in the knowledge workbench. Genesys Dialog Engine Bot Flows allows building bots within Architect and integrating them into Architect call, chat, and message flows, unifying the bot and flow authoring experience. Key features include intents, slots, utterances, confirmations, and learning to build natural language understanding. Architect provides built-in templates, logic, actions, and prompts to customize flows. Advanced features like the Communication Sequence Builder, knowledge, Flow Insights, and intent health improve bot capabilities. Bots leverage AI-powered slots and intent mining to understand customer intents from transcripts. Quick replies, cards, and carousels enable rich media interactions. Architect provides resources to design advanced bots and flows.

Genesys Cloud's conversational AI solution, Genesys Digital Bot Flows, allows you to build bot flows in Architect and then integrate them into message flows, unifying the bot and flow authoring experience. Key capabilities include building digital menus; customizing bots with intents, slots, utterances, and confirmations; leveraging AI-powered slots; testing bot flows; viewing intent health; and integrating virtual agents. The unified bot and flow building experience in Architect provides end-to-end bot development. Genesys Cloud's knowledge workbench allows knowledge authors to create and manage knowledge articles, optimize search, and view knowledge base performance. Knowledge bases contain predefined articles responding to customer queries. Genesys Virtual Agent generates intents and utterances from descriptions to improve conversation understanding. Recommendations for Virtual Agent slot authoring include using AI-powered types and avoiding free form slots. Intent miner analyzes transcripts to detect customer intents, utterances, topics, and phrases importable into digital bot flows. Admins can enable quick replies and cards for structured responses in bot conversations, with guided answers via options, images, titles, text, and, buttons. Carousels allow displaying multiple cards. Other Genesys Cloud resources help design and build bots and flows in Architect.

Genesys Cloud's Virtual Agent is an AI-powered conversational bot system that handles customer interactions across voice and digital channels. The system leverages generative AI to automatically create intents and utterances, enabling natural language understanding in bot flows. Key features include knowledge base content search, automated conversation summaries, wrap-up code generation, and AI-guided interactions. The platform supports personalized self-service interactions to increase deflection rates and offers seamless transfers to human agents when needed. Virtual Agent includes performance analytics through a comprehensive dashboard, AI Studio for guide creation and publishing, and integration with existing bot flows. The system utilizes AI Experience tokens for metering and pricing, supports multiple languages, and allows for both pre-contact optimization and post-contact analysis. Specific capabilities include free-form slot capture, knowledge base article searching, and customizable after-contact settings for improved service continuity.

Genesys Cloud's Virtual Supervisor represents a comprehensive AI-powered solution that transforms interaction analysis and supervisor workflows through automated agent scoring and real-time insights. The system leverages AI capabilities across three core areas: AI Scoring for automated performance evaluations, AI Translate for multi-language transcript conversion, and AI and Insights for detailed interaction analysis. Operating on a metered pricing model, the platform maintains interaction summaries for 10 days and provides extensive analysis of contact reasons, resolutions, action items, and sentiment drivers. The solution integrates seamlessly with Agent Copilot and various complementary features including voice transcription, speech and text analytics, Virtual Agent capabilities, Journey Management, and AI Studio. While Agent Copilot and Virtual Supervisor maintain separate charging structures, the system extends retention beyond the standard period through the interaction details view. The platform supports Virtual Desktop Infrastructure configurations and requires specific permissions, potentially including Speech and Text Analytics integration, to enable supervisors to efficiently manage performance, conduct targeted coaching, and make data-driven decisions for quality management

Genesys Cloud knowledge portal is a self-service support solution that enables customers to search and browse knowledge base articles, chat with bots, or escalate to live agents. The portal integrates with the knowledge workbench to enhance customer experience and reduce contact volume. Key features include knowledge base search functionality, category browsing, chatbot access, and live agent escalation capabilities. Setup involves selecting a knowledge base, configuring the portal within Messenger Configurations, and deploying a deployment snippet to your hosting site. Customization options include welcome/fallback messages, header and background color settings, primary color configuration, top viewed articles display, header background images, category display with custom icons, and the ability to disable functionality or change the knowledge base. The portal improves self-service capabilities while reducing overall customer contacts.

Genesys Cloud's knowledge workbench allows knowledge authors to create and manage knowledge bases with predefined question and answer articles that respond to customer queries. Key capabilities include adding questions and answers to knowledge bases to enable responses to conversations, organizing articles into categories and labels, creating and editing articles for different touchpoints like bots and agents, viewing article analytics, optimizing knowledge bases by improving article quality, and integrating third-party knowledge sources. The knowledge portal presents knowledge articles to customers so they can self-serve and search articles or initiate conversations with bots or agents. The portal provides resources to help design and build bots and bot flows in Architect, including guides on Genesys Cloud AI, adding knowledge to bots, Genesys Dialog Engine, creating bot flows, building digital bots in Architect, and general bot information. Key capabilities covered include leveraging AI, designing conversations and dialog flows, integrating bots with Genesys Cloud, and using Architect to develop bots. The portal aims to provide comprehensive materials to enable building capable and effective bots on the Genesys Cloud platform.

Genesys Cloud Predictive Engagement is an AI-powered customer engagement solution that analyzes website visitor behaviors, predicts desired outcomes, and personalizes engagements to achieve those outcomes. The platform enables organizations to track customer journeys through segmentation, configure engagement actions including web messaging, web chat, and content offers, and integrate workflows with third-party systems and Salesforce through Architect flows. Core technical capabilities include advanced chat routing, tag manager integration with Google Tag Manager and Adobe Launch, JavaScript SDKs for web and mobile journey tracking, and app event APIs for mobile experiences. The solution provides agents with comprehensive customer journey visualization through journey maps, session information, and interaction data accessible within Genesys Cloud CX, enabling informed customer interactions. Implementation requires tracking journey events using segments, outcomes, and attributes; creating actions and action maps; and managing interactions with embedded customer journey information. Web messaging is the recommended engagement channel, though web chat remains available as an alternative. Mobile journey tracking and targeted messaging offers support proactive customer engagement through action maps. Analytics functionality allows contact center managers and supervisors to access live visitor tracking, visitor activity reports, action map performance metrics, and historical journey data integrated into existing Genesys Cloud performance views. The platform supports campaign tracking capabilities, enabling teams to track campaign-related web activity, create leads with campaign attributes, and allow agents to view and update lead information using scripts. The system includes pre-configured settings with defined limits on maximum entities and web tracking entries per organization. Pricing operates on an event-driven model. Genesys Cloud maintains GDPR compliance for Predictive Engagement data and provides detailed glossary and FAQ resources. Organizations using web messaging exclusively should note that certain Predictive Engagement features may not apply to their configuration.

Genesys Cloud's predictive routing leverages machine learning to optimize key performance indicators (KPIs) by intelligently matching interactions with the most suitable available agents across multiple channels including voice, email, asynchronous messaging, third-party messaging platforms, inbound SMS, web messaging, and open messaging. The system incorporates custom KPI configuration, next contact avoidance, workload balancing, and skill matching capabilities to enhance routing efficiency and operational performance. The AI-driven agent selection operates with full transparency while preventing bias by excluding personally identifiable information (PII) from routing decisions. The platform draws from both mandatory and optional data sources to inform intelligent routing with fallback scenario support, ensuring decisions are based on relevant performance metrics rather than demographic factors. Organizations can assess queue benefits through detailed performance reports tracking interaction processing, agent scores, routing methods, and queue impact analysis. Comparison testing is available against standard or bullseye routing methods to evaluate effectiveness and measure ROI. Queue configuration options include timeout settings, mixed media handling, and KPI processing phases to accommodate diverse operational requirements. The platform provides extensive reporting and monitoring capabilities offering visibility into AI model scoring mechanisms and features influencing routing decisions. Users can access information about data sources used in predictive routing decisions and view predictive routing comparison test results, queue performance metrics, queue detail reports, and queue impact assessments through a Queues view. The system implements documented processes for both standard routing and fallback scenarios to ensure consistent interaction handling. Genesys Cloud includes billing and usage tracking functionality, allowing organizations to monitor predictive routing charges and view comprehensive usage summaries to enable ROI analysis. Additional resources support configuration management, permissions administration, and continuous value monitoring to systematically optimize routing strategies and maximize operational efficiency across all customer interaction channels

Genesys Cloud's speech and text analytics features provide automated capabilities to gain insights into customer-agent conversations through sentiment analysis, topic trends, voice transcription, agent empathy analysis, interaction categories, digital transcripts, interaction overview, and more. These insights highlight areas of improvement, recognition, and concern to better understand and serve customers and employees. Key capabilities include analyzing 100% of interactions, discovering topics and phrases of interest, determining customer sentiment, evaluating agent empathy, categorizing interactions, transcribing calls, monitoring audio, and enhancing transcription with dictionary management. The platform enables businesses to uncover deep insights from conversations to boost customer experience.

creation date, and modification date. Data ingestion rules support keyword-based filtering through multiple operators: Post Includes (primary keywords), Post Also Includes (AND operator keywords), Post does not include (exclusion keywords), and advanced search modes using OR operators (matching either condition), Space operators (AND logic), and Dash operators (NOT logic for exclusion). Location-based filtering enables viewing posts from users matching both keyword criteria and specified profile locations. Organizations can create up to 50 data ingestion rules by default, with limits expandable to 100, 250, or 500 through Genesys Support requests. Administrative controls enable comprehensive rule management through the Admin menu under Message > Social Listening, allowing users to create, edit, pause, and delete rules with support for advanced search capabilities. Rule status management includes three options: Active (default, enabling message receipt), Paused (disabling data collection), and System Paused (automatically triggered when reaching platform limits). Data collection is governed by platform-specific limits, with X platform interactions capped at 200,000 posts by default, expandable to 500,000, 1 million, 2 million, 5 million, 10 million, or 25 million posts. Separate limits apply to Facebook, Open social messaging, and Instagram channels. Detailed usage monitoring is available at organization, platform, and topic levels with historical tracking via the Usage History tab, displaying current billing month data collection details and platform-specific or total usage breakdowns by month and year. Administrators can view data usage estimations for X channel rules over the preceding 28 days based on configured keywords and location selections. The system automatically prevents excess data collection through built-in safeguards that pause rules when thresholds are reached. Access requires appropriate Genesys Cloud CX licensing (versions 1-4 or Digital variants), Genesys Cloud CX AI Experience license, AI Experience tokens, and platform-specific permissions for topic and data ingestion rule management. X platform access requires an additional premium channel fee bundle. Topic management capabilities include adding new topics with names up to and optional descriptions, assigning topics to specific divisions, viewing detailed topic information, editing topic parameters, and deleting topics individually or in bulk. When deleting topics, users must manually remove corresponding data ingestion rules, as they do not delete automatically

Genesys Cloud's Automatic Best Method forecasting uses built-in capabilities for data cleanup, pattern detection, and advanced time-series techniques to create highly accurate individual forecasts. It leverages outlier identification, mathematical fixes, and ensemble forecasting to select the optimal combination of over 20 methodologies that minimize error for each forecast. Key capabilities include automated historical data cleanup, calendar effect handling, detecting seasonality and trends, and blending multiple models like ARIMA and moving average into a single ensemble forecast.

Genesys Cloud offers two primary AI experience bundles designed as add-on offerings to enhance artificial intelligence capabilities within Genesys Cloud subscriptions. The Genesys Cloud CX AI Experience for Digital package includes 1,000 digital bot sessions (1,300 for concurrent licensing), 20,000 Predictive Engagement events (26,000 for concurrent licensing), 1,000 predictive routing interactions, unlimited knowledge workbench and support center access, and Agent Assist capabilities for named agents. The standard Genesys Cloud CX AI Experience bundle includes all Digital package features plus an additional 1,000 voice minutes for Dialog Engine Bot Flows. Both bundles provide access to Dialog Engine bot flows, Digital bot flows, Predictive Engagement, predictive routing, knowledge workbench, support center functionality, and exclude third-party AI applications. Implementation requires one of the base licenses: Genesys Cloud CX 2, CX 2 Digital, CX 3, CX 3 Digital, or CX 4, along with appropriate billing permissions (All, Add, and View). Pricing operates on an annual pre-paid basis calculated on an aggregate per-agent basis across multiple currencies. The Genesys Cloud CX AI Experience for Digital is priced at $40 USD/$44 CAD/$52 AUD/$56 NZD/$28 GBP/$32 EUR/160 BRL/7,200 JPY/568 ZAR per agent annually, while the standard CX AI Experience package costs $60 USD/$66 CAD/$78 AUD/$84 NZD/$42 GBP/$48 EUR/240 BRL/7,200 JPY/852 ZAR per agent annually. Volume discounts are available through Customer Success Managers. Individual native AI products are also available for purchase à la carte, and sales representatives can provide additional information regarding specific implementations and volume considerations. The 2024 pricing update reflects branding changes and clarifies aggregate pricing methodology, with this documentation addressing legacy per-invocation rate structures; alternative per-turn/minute metering options are documented separately