HanseWatt — Agentforce service for DACH energy
An AI-powered customer service platform for a fictional Hamburg energy retailer: an autonomous, German-speaking Agentforce agent grounded in unified consumption and billing data (Data 360), under the Einstein Trust Layer. Currently in development.
- Year
- 2026
- Role
- Salesforce Developer / Solution Architect
- Tech stack
- Service CloudAgentforceData 360 (Data Cloud)Einstein Trust LayerApexLightning Web ComponentsKnowledgeOmni-ChannelSFDX (8 packages)Kevin O'Hara trigger framework
Highlights
- Sell vs Serve: the 'serve' counterpart to TechnoStore — Service Cloud + Agentforce + Data 360
- Autonomous German-speaking service agent, grounded in unified data under the Einstein Trust Layer (GDPR/DSGVO)
- Phase 1 shipped: 7 custom objects + 37 fields, Case + SLA entitlement, Omni-Channel routing
- Knowledge base: a 6-topic data-category group with 10 published, categorized articles
- Security: 3 permission sets (bills/readings read-only = system-of-record); multi-currency EUR + CHF
- Designed across 19 Architecture Decision Records (Nygard format)
- In development: Data 360 ingestion, identity resolution, calculated insights, and the grounded agent are next
The problem
DACH energy retailers field a flood of repetitive, German-language service contacts — 'why is my bill so high?' — that need accurate, data-grounded answers and safe, auditable action, not a chatbot that guesses. The hard part is grounding an LLM in unified consumption + billing data, letting it take real action (create cases, initiate tariff changes), and escalating safely to a human — all GDPR/DSGVO-compliant under the Einstein Trust Layer.
Architecture
Customer channels (web chat, WhatsApp, Experience Cloud) reach an Agentforce Service Agent — topics, actions, and instructions running under the Einstein Trust Layer (PII masking, grounding, audit). Grounding (RAG) pulls from German Knowledge articles and Data 360 DMOs; an Apex action layer (GetLatestBill, ExplainAnomaly, CreateCase, InitiateTariffChange) takes real action against the Service Cloud core (Account, Contact, Case with record types + SLA, Knowledge, Omni-Channel) and custom objects (Meter__c, Tariff__c, Service_Contract__c, Energy_Bill__c…). Underneath, Data 360 ingests smart-meter and SAP IS-U billing data (Ingestion API / MuleSoft) → DLO → DMO → identity resolution → unified profile, with calculated insights (avg kWh, anomaly, churn) driving segments and proactive outreach — closing the loop from reactive service to proactive prevention.
The approach
Built in gated phases with honest framing: external systems (smart-meter MDM, SAP IS-U) are simulated, while the Salesforce code paths, the agent, the Data 360 model, and the grounding are real. The SFDX org is split into eight packages (core, services, actions, handlers, agent, datacloud, lwc, tests) so architectural boundaries are visible at the filesystem level, and every trigger extends the Kevin O'Hara TriggerHandler framework. Phase 1 (Service Cloud core) is deployed and committed; Data 360 ingestion, identity resolution, calculated insights, the grounded Agentforce agent, prompt templates + Trust Layer, and escalation flows are the next phases — with agent evaluation and red-teaming in the second wave.
The outcome
Phase 1 is live: a 7-object energy data model (37 fields), Case management with record types and an SLA entitlement (4h first response, 2-business-day resolution), Omni-Channel routing with German + Billing skills, a 6-topic Knowledge base of 10 published articles, three permission sets, and multi-currency (EUR + CHF) with seeded DACH demo data — documented across 19 Architecture Decision Records. It's actively in development toward the full grounded-agent demo: the 'serve' half of the enterprise that complements TechnoStore's 'sell' half.