Cert++
  1. Home
  3. Agentforce Service Consultant

Agentforce Service Consultant

Checklist progressProgress

0/254Learned

Agentforce Service Consultant Study Checklist
  • Platform Administrator
  • Platform App Builder
  • Platform Foundations
  • Platform Developer
  • Platform Administrator II
  • Agentforce Sales Consultant
  • Agentforce Service Consultant
  • Platform Data Architect
  • Platform Development Lifecycle and Deployment Architect
  • Platform Identity and Access Management Architect
  • Platform Integration Architect
  • Platform Sharing and Visibility Architect
  • Heroku Architect
  • B2C Solution Architect
  • Experience Cloud Consultant
  • Agentforce Field Service and Operations Consultant
  • Agentforce Nonprofit Consultant
  • Data 360 Consultant
  • Omnistudio Consultant
  • CRM Analytics and Einstein Discovery Consultant
  • Platform User Experience Designer
  • Platform Strategy Designer
  • B2C Commerce Developer
  • JavaScript Developer
  • Omnistudio Developer
  • Platform Developer II
  • Marketing Cloud Engagement Administrator
  • Marketing Cloud Engagement Specialist
  • Marketing Cloud Engagement Consultant
  • Agentforce Sales Foundations
  • Business Analyst
  • Marketing Cloud Engagement Developer
  • Marketing Cloud Engagement Foundations
  • Agentforce Specialist
  • Agentforce Life Sciences Consultant
  • B2B Commerce Administrator AP
  • B2B Commerce Developer AP
  • Agentforce Consumer Goods AP
  • Agentforce Financial Services AP
  • Agentforce Health AP
  • Agentforce Manufacturing AP
  • MuleSoft Integration Foundations
  • MuleSoft Developer
  • MuleSoft Developer II
  • MuleSoft Platform Integration Architect
  • MuleSoft Platform Architect
  • Tableau Desktop Foundations
  • Tableau Data Analyst
  • Tableau Consultant
  • Tableau Server Administrator
  • Tableau Architect
  • Slack Administrator

Checklist progressProgress

0/254Learned

  • Core components of contact center management
  • Call center metrics versus omnichannel contact center metrics
  • Average handle time components and drivers
  • Speed to answer, service level and abandonment drivers
  • First contact resolution drivers
  • Case resolution time and SLA attainment drivers
  • CSAT versus NPS as service KPIs
  • Customer effort score and effort drivers
  • Case deflection rate drivers
  • Cost per contact and the drivers that lower it
  • Rep occupancy, burnout and retention
  • Efficiency metrics versus customer experience trade-offs
  • Business policy and data definitions behind KPI values
  • AI agents and AI assistance effects on service KPIs
  • Prebuilt analytics for contact center KPIs and AI impact
  • Uncovering the root business challenge behind a requested solution
  • Needs, wants and expectations when prioritizing client requirements
  • Business case and case for change for a service transformation
  • Disconnected channels and siloed customer data as a service challenge
  • Handoff challenges between frontline support and technical teams
  • Identifying and categorizing risks in a service implementation
  • Scope creep and triple-constraint trade-offs
  • Benefits, risks and ROI goals of a self-service portal
  • Benefits and risks of introducing AI agents into customer service
  • Data readiness as a risk to AI-driven service outcomes
  • Consultant activities across the customer engagement lifecycle
  • Identifying and managing service implementation stakeholders
  • Customer-centric discovery steps for a service engagement
  • Gathering service requirements across support stakeholders
  • Defining measurable success criteria at the start of an engagement
  • Building a business case for an Agentforce Service investment
  • Prioritizing service requirements into a right-sized scope
  • Statement of work and change control for implementation scope
  • Co-creating a phased change roadmap with stakeholders
  • LEVERS model for leading change in a service rollout
  • Phased, pilot and big-bang rollout approaches for service teams
  • Deployment timing and release cadence for contact center operations
  • Sandbox types for user acceptance testing and training environments
  • Launch communication plan by rollout stage
  • Super users, early adopters and executive sponsors as adoption champions
  • Core elements of a user training strategy
  • Role-based training plans for service users
  • Choosing training delivery methods for audience, scale and budget
  • In-app guidance and custom Help Menu for learning in the flow of work
  • Assigning and tracking training completion
  • Post-go-live support model and ongoing refresher training
  • Measuring and recognizing user adoption after launch
  • Staged launch and testing of an Agentforce Service agent
  • Rollout and enablement strategy for AI-assisted rep features
  • Scoping which legacy service data to migrate
  • Object load sequence for service data migrations
  • Choosing a data loading tool for a service migration
  • Suspending validation rules, triggers, and automation during large loads
  • Deferring sharing calculations during large data loads
  • Test loads and validation before a production data cutover
  • Planning a Classic to Lightning Knowledge migration
  • Assessing and improving service data quality before and after migration
  • Data quality readiness for Agentforce grounding
  • Data governance framework roles and components
  • Data governance controls for regulated service data
  • Large data volume risks and up-front data model planning
  • Data skew in service data models
  • Data tiering with archiving and external objects for large data volumes

Given a scenario, analyze customer requirements to determine an appropriate solution design considering capabilities, limitations, and trade-offs for the service agent experience

0/12

Human-centric principles for the service rep experience

Learn this concept
Unseen

Lightning console navigation for multitasking service reps

Learn this concept
Unseen

Dynamic Forms and Dynamic Actions on case record pages

Learn this concept
Unseen

Surfacing customer and related-record context for reps

Learn this concept
Unseen

Knowledge access in the rep workspace

Learn this concept
Unseen

Macros versus quick text for repetitive rep tasks

Learn this concept
Unseen

Guided screen flows and Actions and Recommendations for reps

Learn this concept
Unseen

Einstein Case Classification and Article Recommendations for reps

Learn this concept
Unseen

Generative reply drafts and conversation summaries for reps

Learn this concept
Unseen

Service Assistant service plans and record summaries

Learn this concept
Unseen

Unified voice and messaging workspace for reps in Agentforce Contact Center

Learn this concept
Unseen

Standard features versus custom or AgentExchange solutions

Learn this concept
Unseen

Given a scenario, analyze customer requirements to determine an appropriate solution design considering capabilities, limitations, and design trade-offs for the customer experience

0/10

  • Customer journey mapping to shape service experience requirements
  • Channel mix design for customer contact preferences and issue urgency
  • Tiered service model across self-service, AI agents and service reps
  • Experience Cloud help center versus authenticated customer portal
  • Agentforce Service agent on an Experience Cloud self-service site
  • Default versus specialized Agentforce Service agent templates
  • Escalation from Agentforce Service agents to service reps
  • Context continuity and personalization across customer channels
  • Transparency with customers about AI agents and recorded conversations
  • Language coverage for AI agents serving multilingual customers

Given a set of customer data security and compliance requirements, determine a successful design to secure the data

0/14

  • Case record visibility across support teams and tiers
  • External customer case access on Experience Cloud sites
  • Knowledge article visibility with data categories and channels
  • Agent user object and record access under least privilege
  • Service agent run-as context by customer authentication level
  • Authentication patterns for service agents by deployment channel
  • Customer verification and scoping of private agent actions
  • Einstein Trust Layer protections for Agentforce Service agents
  • Field-level security versus Shield Platform Encryption for sensitive data
  • Sensitive data protection in messaging sessions and voice calls
  • Messaging channel selection under HIPAA and regulated-data requirements
  • Consent and communication preference tracking for service customers
  • Audit trail and field history options for service compliance
  • Fulfilling customer data deletion and portability requests
  • Knowledge-Centered Service core principles and benefits
  • KCS Solve Loop steps during case handling
  • KCS Evolve Loop and article quality audits
  • Knowledge article publishing cycle and archiving
  • Article Validation Status versus publication status
  • Updating published articles and article version history
  • Knowledge record types, page layouts and article fields
  • Data category groups, hierarchies and visibility
  • Knowledge access for readers, authors and KCS publishers
  • Article approval processes and publishing automation
  • Multilingual knowledge base and article translation
  • Knowledge base planning for a new implementation
  • Importing existing content and moving to Lightning Knowledge
  • KCS program adoption: leadership, coaching and agent buy-in
  • Article channels for internal, customer, partner and public audiences
  • Separating internal notes from customer-facing article content
  • Knowledge component on case pages in the console
  • Sharing Knowledge articles with customers from a case
  • Suggested Articles versus Einstein Article Recommendations
  • Knowledge article access for site members and guest users
  • Topics and data categories for articles in Experience Cloud sites
  • Knowledge search tuning with synonyms and promoted terms
  • Measuring article usage and helpfulness
  • Einstein Knowledge Creation for drafting articles from cases
  • Grounding Agentforce service agents in Knowledge articles
  • Intake channel mix for customer and business requirements
  • Email-to-Case intake design: variants and routing addresses
  • Web-to-Case capture, spam protection and limits
  • Web-to-Case versus Experience Cloud self-service case submission
  • Enhanced Chat for website and mobile app intake
  • Apple Messages for Business journey planning and entry points
  • Third-party messaging app channels for a customer base
  • Capability differences across enhanced messaging channels
  • Messaging components for interactive service conversations
  • Rep transfer, conferencing and supervisor help in messaging sessions
  • Proactive outbound messaging and automated notifications
  • Voice channel capabilities for reps and supervisors
  • Social media channels for customer service
  • Unified customer conversation history across channels
  • Bring Your Own Channel for Messaging versus BYOC for CCaaS
  • Standard versus enhanced messaging channels
  • Messaging setup prerequisites and licensing
  • Omni-Channel routing configurations and work prioritization
  • Skills-based versus queue-based Omni-Channel routing
  • Queue-based routing versus Omni-Channel flows for messaging channels
  • Tab-based versus status-based Omni-Channel capacity models
  • Presence configurations and after-conversation work time
  • Quick text versus reply recommendations for messaging reps
  • Messaging consent and sensitive data protection
  • Omni Supervisor for real-time channel monitoring
  • Reporting on messaging channels and sessions
  • Assessing which service work suits an autonomous AI agent
  • Planning and prioritizing AI agent use cases against business goals
  • Choosing among Agentforce agent types for a service need
  • When to recommend Einstein Bots instead of an AI agent
  • Combining an Einstein bot and an AI agent in one conversation path
  • Agentforce Service Agent versus Einstein Bots capabilities
  • Service agent setup prerequisites, versioning and activation
  • Configuring subagents, instructions and actions for a service agent
  • Grounding service agent answers with Agentforce Data Library
  • Context variables and customer verification in agent conversations
  • Channel deployment options for an Agentforce Service agent
  • Agent connections and adaptive response formats across channels
  • Inbound and outbound Omni-Channel flows for AI agent routing
  • Escalation subagent and handoff from AI agent to service reps
  • Agentforce Service agent on email and incoming case processing
  • Testing and reviewing service agent behavior
  • Migrating from Einstein Bots with the Create Agent from Bot tool
  • Stages of the case resolution process
  • Support processes and case record types for distinct case lifecycles
  • Email-to-Case versus Web-to-Case for automated case creation
  • Case sharing model and taking ownership of queued cases
  • Case feed quick actions and case comments
  • Case Timeline and Case History for tracking case activity
  • Case teams and swarming for collaborative case resolution
  • Parent and child case hierarchies for grouping or splitting work
  • Case merge and Enhanced Case Merge for duplicate cases
  • Case closure design and closed status behaviour
  • Customer feedback surveys versus evaluation forms for case quality
  • Aligning case lifecycle design to service KPIs
  • Customer Service template self-service site built on Knowledge
  • Case Deflection component paired with the Contact Support Form
  • Guided self-service flows and account actions that avoid a case
  • Grounding a customer-facing agent in Knowledge for deflection
  • Fallback paths from site self-service to a service rep
  • Capturing deflection feedback with Deflection Metrics and Deflection Tracking
  • Reporting on site case deflection effectiveness
  • Matching deflection requirements to site, Knowledge or Agentforce features
  • Entitlement management building blocks and what each represents
  • Choosing an entitlement management model for support eligibility
  • Service contract line items and entitlement templates for product coverage
  • Assets in entitlement coverage and case lookups
  • Automatically applying entitlements to web, email and site cases
  • SLA policy entry and exit criteria on support records
  • Milestone recurrence types for repeating SLA steps
  • Milestone success, warning and violation actions
  • Auto-completing milestones and controlling manual completion
  • Milestone tracker and rep visibility into SLA countdowns
  • Pausing milestone timers on stopped cases
  • Business hours and support holidays for multi-region support
  • Business hours hierarchy across milestones, SLA policies and cases
  • Entitlement process versioning versus simplified SLA setup
  • Entitlement and service contract access for Experience Cloud users
  • Reporting on entitlement and milestone compliance
  • Case assignment rules versus Omni-Channel routing
  • Automatic case assignment rules for Experience Cloud site cases
  • Auto-response rules versus other automated customer notifications
  • Escalation rules versus entitlement milestone actions
  • Flow Builder versus built-in case rules for service automation
  • Einstein Case Classification versus Einstein Case Routing
  • Assistive AI for service reps versus autonomous service agents
  • Agentic versus deterministic workflow automation for service processes
  • Incident Management versus case hierarchies for service disruptions
  • Matching contact center KPIs to executive, supervisor and rep dashboards
  • Lightning reports versus CRM Analytics, Data 360 and Tableau for service reporting
  • Selecting report types for service data requirements
  • Report formats, groupings and filters for service data
  • Dashboard components and filters for service KPIs
  • Prebuilt service reports and dashboards for contact center supervisors
  • Case report views for queues, case teams, comments and parent cases
  • Measuring first-contact resolution with case reports
  • Case aging and case field history reporting
  • Trending service metrics over time
  • Dynamic dashboards and running user for stakeholder data visibility
  • Report and dashboard subscriptions for stakeholder updates
  • Embedding dashboards and KPIs in the Service Console for reps
  • Command Center for Service real-time monitoring versus historical reporting
  • Contact center KPI reporting for Salesforce Voice
  • Service Analytics templated app in CRM Analytics
  • Service Intelligence dashboards for supervisors and reps
  • Service Intelligence licensing, data prerequisites and refresh
  • Service Insights versus Service Intelligence
  • Einstein Conversation Mining for identifying contact reasons
  • Service AI Adoption and Analytics dashboard
  • Agent Analytics in Agentforce Studio for AI agent performance
  • Agent Analytics effectiveness, usage and health metrics
  • Data integration considerations and tool selection
  • Integration user licensing and authentication best practices
  • Salesforce Connect virtualization versus replicating data between systems
  • Salesforce Connect adapter selection for external and cross-org data
  • Writable external objects and external data source identity type
  • API-led connectivity and MuleSoft Anypoint connectors
  • Unifying customer data across multiple orgs and external systems
  • Flow options for reaching third-party systems from service processes
  • External Services for declarative calls to external APIs
  • Platform events versus Outbound Messaging for notifying external systems
  • Agentforce Contact Center versus Partner Contact Center telephony integration
  • Voice-enabled Agentforce agents and IVR call flow placement
  • Slack integration for service collaboration and case swarming
  • Customer Service Incident Management integrations with third-party tools
  • Agentforce Commerce and Agentforce Service integration for order-related service
  • Grounding service agents in Salesforce, external and unstructured data
  • Bringing third-party knowledge sources into service search and AI
  • MCP for Agentforce to connect service agents with third-party tools
  • AppExchange packaged solutions versus custom-built integrations

Prepare for the Exam

Play Today's Certle
Back to track

Study Community

Ask questions and get the latest info from other Agentforce Service Consultant studiers. 662 members and growing.

Go to Discord
  1. Agentforce Service Consultant Checklist
  3. Agentforce Service Solution Design

Einstein Case Classification and Article Recommendations for reps

Explainer

Learn More

Practice Question

Keep going

Next conceptGenerative reply drafts and conversation summaries for reps

Checklist progress

0/254 (0%)

0 of 254 concepts learned

Tip: You can filter concepts by status.

Prepare for the Exam

Play Today's Certle
Back to track

Study Community

Ask questions and get the latest info from other Agentforce Service Consultant studiers. 662 members and growing.

Go to Discord
Close
  1. Agentforce Service Consultant Checklist
  3. Agentforce Service Solution Design
Einstein Case Classification and Article Recommendations for reps

Explainer

Learn More

Practice Question

Keep going

Next conceptGenerative reply drafts and conversation summaries for reps

Explainer

Einstein Case Classification and Einstein Article Recommendations are AI features that help service reps handle cases faster in the Lightning Service Console. Case Classification learns from your closed cases to suggest, pre-select or automatically save case field values, and Article Recommendations suggests the Knowledge articles most likely to solve a case. Both learn from your org's historical data, so their accuracy depends on how much good data you have.
Core information
  • Einstein Case Classification uses a model trained on your org's closed cases to predict values for most checkbox, picklist and lookup fields on a case. It makes its recommendations right after a case is created, and reps see them in the Lightning Service Console.
More details and nuances
  • Segments and example cases are both optional filters, but they do different jobs. A segment limits which closed cases Einstein learns from and also which new cases get predictions, so it fits a business unit such as an Enterprise division. Example case criteria limit only which closed cases Einstein learns from, and all new cases can still get predictions. If you use both, the example cases come from within the segment.

Explainer

Einstein Case Classification and Einstein Article Recommendations are AI features that help service reps handle cases faster in the Lightning Service Console. Case Classification learns from your closed cases to suggest, pre-select or automatically save case field values, and Article Recommendations suggests the Knowledge articles most likely to solve a case. Both learn from your org's historical data, so their accuracy depends on how much good data you have.
Core information
  • Einstein Case Classification uses a model trained on your org's closed cases to predict values for most checkbox, picklist and lookup fields on a case. It makes its recommendations right after a case is created, and reps see them in the Lightning Service Console.
More details and nuances
  • Segments and example cases are both optional filters, but they do different jobs. A segment limits which closed cases Einstein learns from and also which new cases get predictions, so it fits a business unit such as an Enterprise division. Example case criteria limit only which closed cases Einstein learns from, and all new cases can still get predictions. If you use both, the example cases come from within the segment.