Demo-Lab

Build custom Lightning Types (CLTs) that render rich UI inside an Agentforce chat window — Service Agent (Enhanced Chat v2), Employee Agent (LEX assist panel), and Mobile. TRIGGER when the user asks to build, customize, or debug a custom Lightning Type for Agentforce; render forms, cards, carousels, file uploads, or interactive components in an agent chat; or works in a `lightningTypes/**` folder, edits an LWC with `lightning__AgentforceInput`/`lightning__AgentforceOutput` targets, or wires an agent action's "Output Rendering" to a custom LWC. DO NOT TRIGGER for object-based Lightning Types intended for Experience Builder or Prompt Builder only (use object schema patterns directly), MIAW (non–Chat V2) deployments, or plain LWCs on record/app/home pages.

Enable Agentforce for Service AI features on native Voice in Agentforce Contact Center. Use when turning on Conversation Catch-Up for Voice and configuring Work Summaries for Voice — creating summary fields and a quick action, adding Einstein Field Recommendations to the Voice Call page, and mapping summary fields with Voice Call as the response destination.

Configure an Agentforce Voice agent on native Salesforce Voice in Agentforce Contact Center. Use when connecting an Agentforce Service Agent to Telephony, building the inbound routing and escalation Omni-Channel flows, tuning voice settings (voice profile, stability, pronunciation), and enabling seamless escalation to a human rep with full context.

End-to-end build orchestrator for Agentforce Contact Center (AFCC) with native Salesforce Voice. Use when standing up a comprehensive AFCC voice agent from scratch — sequencing licenses, the Voice channel, Agentforce Voice, Agentforce for Service, Command Center, and advanced IVR/callbacks — and to decide which focused AFCC skill to hand off to next.

Configure callback requests for native Salesforce Voice in Agentforce Contact Center. Use when setting up the Contact Request object with Omni-Channel, creating a callback service channel and queue, building a callback flow that captures a number and creates a Contact Request, and enabling automatic outbound dialing when a rep accepts.

Configure Command Center for Service (supervisor experience) in Agentforce Contact Center. Use when setting up Supervisor Configurations, choosing visible tabs and visible Agentforce agents for monitoring/listen-in, and installing the Command Center Service reports and dashboards (including the Voice Calls report-type conflict workaround).

Build IVR into Omni-Channel flows for native Salesforce Voice in Agentforce Contact Center. Use when adding Play Prompt elements, capturing DTMF input, branching on caller response, controlling speech with SSML, choosing voice profiles/languages, playing media prompts, and ending or controlling recording on a call path.

Manage audio media for native Salesforce Voice in Agentforce Contact Center. Use when uploading .mp3/.wav files, organizing the media library, creating and assigning custom and default media labels for IVR prompts, welcome messages, hold music, and recording announcements, and cleaning up unused media.

Diagnose and fix common Agentforce Contact Center native Voice demo issues. Use when calls won't connect or take multiple tries, calls reach a queue but not the agent, Agentforce Voice escalation never transfers, the agent's tone is inconsistent, Omni-Channel shows reconnecting, callbacks stay stuck dialing, voice reports won't install, or work summaries come back blank.

Stand up the native Salesforce Voice channel in Agentforce Contact Center. Use when assigning AFCC permissions, claiming a phone number, configuring and activating the Voice channel, setting caller line identification, enabling recording/transcription, tuning the Voice routing configuration, and building the Voice Call record page.

Give an Agentforce agent the ability to "see" — analyze a customer-uploaded photo (device, error screen, status light, fault code) on-platform and act on what it shows. Use when building or debugging vision/multimodal Agentforce agents, image analysis actions, or when the user mentions photo troubleshooting, "agent that can see", image diagnosis, ContentDocument to a vision model, or a flex prompt template bound to an image.

Agent API citations — parsing and rendering cited sources returned by an agent. Use when handling the citedReferences array in an Inform response, rendering source lists or inline citations via inlineMetadata (claim + location), or linking cited records back to Salesforce.

Agent API integration architecture — website chat, headless automation, platform connectors, and agent-to-agent patterns. Use when designing where and how to embed the Agentforce Agent API, structuring a client (token service, session manager, message loop, streaming handler), and setting the security and resilience posture for a production integration.

Agent API messaging — synchronous and streaming (SSE) message sending, sequenceId management, and streaming event handling. Use when building the send-message loop for an Agentforce Agent API client, consuming server-sent events (ProgressIndicator, TextChunk, Inform, EndOfTurn, ValidationFailureChunk), or choosing between the sync and stream endpoints.

Review rubric for Agentforce Agent API integrations. Use when auditing or reviewing an Agent API client/integration for auth and secret handling, session hygiene, sequence and concurrency correctness, streaming resilience, variable safety, citation rendering, error handling, billing awareness, and Government Cloud readiness.

Agent API session lifecycle — start a session, maintain conversation context, end a session, and submit feedback. Use when designing or building the session flow for an Agentforce Agent API integration, managing session IDs and sequence IDs, choosing sync vs streaming messaging, or handling session end reasons and feedback submission.

Agent API onboarding — External Client App (ECA), OAuth client credentials flow, token minting, and agent ID retrieval. Use when setting up access to the Salesforce Agentforce Agent API, configuring the ECA/OAuth scopes, generating a bearer token, resolving My Domain and base endpoints, or finding an agent's ID for use in API calls.

Agent API troubleshooting — diagnose HTTP 400/401/404/423/500 responses, timeouts, media-type errors, and Government Cloud endpoint issues. Use when an Agentforce Agent API call fails, returns an error status, times out, or when diagnosing EngineConfigLookupException / HttpServerErrorException / Session Already Locked errors.

Agent API context and custom variables — passing session context to an agent and configuring variable accessibility. Use when sending context variables ($Context.*) or custom variables through the Agent API, controlling editability across turns, or configuring ConversationVariable / ConversationContextVariable via Agentforce Builder or Metadata API.

Service Cloud feature-to-API/CLI mapping and deployment planning. Use when translating Service Cloud features into metadata deploys, data API operations, and repeatable sf CLI execution plans.

Contact center and digital channel configuration for Service Cloud. Use when planning Voice, Messaging, Embedded Service, CTI, and channel-object metadata deployment with CLI runbooks.

Service Cloud data-only configuration strategy. Use when features are API-capable but not metadata-deployable and must be moved with data APIs, scripts, or seeded records.

Experience Cloud and self-service Service Cloud configuration planning. Use when designing deployable site, knowledge, topic, audience, and embedded service configuration bundles.

Live-call AI form-fill experiences for Service Cloud Voice. Use when designing or building configurable intake templates that listen to the live transcript, extract structured answers via the Models API, suggest non-destructive answers in the UI, and dispatch results to a target SObject. Composes sf-service-voice-toolkit and sf-service-models-api.

Trust Layer GenAI integration via aiplatform.ModelsAPI from Apex. Use when designing or building model selection, prompt strategy, structured output, response parsing, and operational controls for LLM calls embedded in Service Cloud workflows (case summarization, classification, extraction, drafting, agent assist).

Real-time voice transcript integration patterns for custom LWCs on the VoiceCall record page. Use when designing or building agent assist, coaching, sentiment, form-fill, or compliance components that consume the live transcript via Service Cloud Voice Toolkit API or ConversationEntry fallback.

Salesforce Messaging API and Conversation Toolkit API implementation guidance. Use when building custom messaging clients, orchestrating agent handoff, sending/receiving messages, or managing conversation sessions and participant context in Service Cloud.

Service Cloud case lifecycle design and optimization. Use when designing case record models, status flows, assignment ownership, escalation paths, closure criteria, or backlog triage in Service Cloud.

Service Console productivity design patterns. Use when optimizing console layouts, utility bar tools, macros, quick text, split view, and agent throughput for Service Cloud teams.

Email-to-Case design and hardening patterns for Service Cloud. Use when implementing email intake, threading, parsing, auto-response rules, assignment logic, and spam/noise controls.

Entitlements and milestone design for Service Cloud SLA management. Use when configuring entitlement processes, milestone timers, violation handling, and business-hours-aware support commitments.

Service Cloud to Field Service handoff patterns. Use when orchestrating escalation from contact center resolution attempts into onsite dispatch, work orders, and technician feedback loops.

Service Cloud major incident workflow design. Use when creating incident intake, severity classification, swarm operations, stakeholder communications, and post-incident closure patterns.

Service Cloud Knowledge strategy and implementation guidance. Use when designing article types, data categories, publication workflows, channel visibility, and knowledge-centered support operations.

Omni-Channel routing strategy for Service Cloud. Use when configuring queues, routing rules, skills-based routing, presence statuses, and capacity planning across support channels.

Service Cloud solution quality review with a weighted rubric. Use when auditing Service Cloud designs or implementations for case operations, routing, SLA controls, channel readiness, and operational risk.

Voice and digital engagement architecture for Service Cloud. Use when designing support workflows for voice, chat, SMS, messaging, and asynchronous digital channels with unified agent operations.

Customer Success Manager / Technical Account Manager that owns the post-sale relationship — adoption, health scores, expansion, and renewal. Shifts the conversation from "why buy Salesforce" to "how to get more value from what you already own." Creates success plans, adoption scorecards, health check reports, expansion opportunity maps, QBR decks, risk mitigation plans, and feature adoption playbooks. TRIGGER when: success planning, adoption tracking, health scores, customer health checks, expansion opportunity mapping, QBR preparation, renewal strategy, risk mitigation, feature adoption analysis, customer feedback synthesis, onboarding-to-value planning, license utilization reviews, or executive business reviews. DO NOT TRIGGER when: pre-sale strategy (use sf-dse), deal-level selling or demo prep (use sf-se), requirements for new projects (use sf-ba), writing Apex code (use sf-apex), building LWC (use sf-lwc), or configuring metadata (use sf-metadata).

Salesforce Demo Engineer responsible for demo environment setup, sample data generation, demo reset procedures, environment runbooks, and demo reliability. Owns the technical infrastructure that makes demos repeatable and believable. TRIGGER when: user sets up demo orgs, generates sample/persona data, creates demo reset procedures, builds demo data plans, maintains demo environments, maps environment dependencies, curates persona-based test data, or asks for demo reliability review. DO NOT TRIGGER when: demo narrative or strategic framing (use sf-dse), deal strategy or account planning (use sf-se), requirements gathering or user stories (use sf-ba), production deployments (use sf-deploy).

Deep vertical expertise and regulatory context for Salesforce implementations. Enriches every other role with industry-specific knowledge — regulations, terminology, KPIs, buying patterns, and process patterns per vertical. TRIGGER when: industry-specific process mapping, regulatory compliance requirements, vertical terminology translation, industry KPIs/benchmarks, industry data models, industry-specific Salesforce clouds (Health Cloud, Financial Services Cloud, Communications Cloud, Manufacturing Cloud, Consumer Goods Cloud, Public Sector Solutions, Education Cloud, Nonprofit Cloud), cross-industry pattern transfer, or any conversation where vertical context materially changes the recommendation. DO NOT TRIGGER when: generic platform work without industry context (use the matching sf-* skill), Apex code (use sf-apex), solution architecture without vertical nuance (use sf-sa).