Agentic, Assistive & Predictive AI Design Patterns
Building AI isn’t just about prompting or plugging into an API — it’s about architecture. This workshop translates Salesforce’s Enterprise Agentic Architecture blueprint into practical design patterns for real-world builders.
You’ll explore how Predictive, Assistive, and Agentic patterns map to Salesforce’s Agentforce maturity model, combining orchestration, context, and trust into cohesive systems. Through hands-on modules, participants design a Smart Checkout Helper using Agentforce, Data Cloud, MCP, and RAG—complete with observability, governance, and ROI mapping.
Key Takeaways
Agentic Architecture Foundations: Understand multi-agent design principles — decomposition, decoupling, modularity, and resilience.
Pattern Literacy- Apply patterns: Orchestrator, Domain SME, Interrogator, Prioritizer, Data Steward, and Listener.
Predictive–Assistive–Agentic Continuum: Align AI maturity with business intent — from prediction and guidance to autonomous execution.
RAG Grounding & Context Fabric: Integrate trusted enterprise data via Data Cloud and MCP for fact-based reasoning.
Multi-Agent Orchestration: Implement Orchestrator + Worker topologies using A2A protocol, Pub/Sub, Blackboard, and Capability Router.
Governance & Trust: Embed privacy, bias mitigation, observability, and audit trails — design for CIO confidence.
Business Alignment: Use the Jobs-to-Be-Done and Agentic Map templates to connect AI outcomes with ROI.
Agenda
Module 1 – Enterprise Agentic Foundations
- Why multi-agent architecture > monolithic AI.
- Core principles: decomposition, decoupling, specialization, modularity.
- Explore: Agentforce subsystems, Atlas Reasoning Engine, MCP, and A2A protocol.
- Build: “Hello Agentforce” → Orchestrator + Worker Agent handshake.
Module 2 – The Big 3 Patterns: Predictive, Assistive, Agentic
- Understand foresight → guidance → autonomy.
- Map Salesforce maturity levels (1–4) to each pattern.
- Build: Cart abandonment handled via Predictive, Assistive, and Agentic variants.
Module 3 – Predictive AI → Foresight in Systems
- Forecast churn, fraud, demand with Data Cloud + Einstein GPT.
- Pattern Fusion: Prioritizer + Generator + Predictive flow.
- Build: Predictive scoring embedded in checkout journey.
Module 4 – Assistive AI → Guiding Humans
- UX patterns: nudges, cards, contextual insights.
- Listener/Feed Pattern for real-time context surfacing.
- Build: Service Agent + Promotion Recommender (Next Best Action).
Module 5 – Agentic AI → Autonomy in Action
- Orchestrator Pattern as Agentic Front Door.
- Domain SME Pattern for Inventory or Orders.
- Interrogator for context assembly and reasoning.
- Build: Refund Agent with human-in-loop fallback and A2A coordination.
Module 6 – Agentic Map & Jobs-to-Be-Done Framework
- Learn the Agentic Map Template (User, Agent, Context, Source layers).
- Use JTBD to align patterns with business goals.
- Exercise: Map Acquire → Convert → Fulfill → Support journeys to AI patterns.
Module 7 – RAG & Context Fabric
- Why hallucinations occur and how RAG fixes them.
- Combine vector DB + retriever + Agentforce knowledge actions.
- Build: Checkout FAQ bot (returns, policies, catalog) with citations.
Module 8 – Multi-Agent Orchestration with MCP
- Orchestrator/Supervisor → Worker → Capability Router flow.
- Pub/Sub for events, Blackboard for shared memory.
- Build: Checkout Agent → Inventory Agent → Pricing Agent → Orchestrator.
Module 9 – Governance & Guardrails
- Identity & Access, Privacy, Bias Checks, Observability.
- Patterns: Data Steward + Zen Data Gardener for trusted data ops.
- Build: Add governance and logging to prototype via MCP telemetry.
Module 10 – From Prototype to Production
- End-to-end demo of Smart Checkout Helper.
- Agentic Pattern Matrix + Governance Checklist + ROI Storytelling.
- Next steps for scaling Agentforce in your enterprise.
What You’ll Leave With
- Working Smart Checkout Helper (Agentforce + MCP + RAG).
- Decision Framework: Predictive vs Assistive vs Agentic.
- Governance Checklist for trust & auditability.
- Multi-Agent Playbook (Orchestrator, Supervisor, Capability Router).
- Agentic Map Toolkit linking JTBD → AI → ROI.
About Rohit Bhardwaj
Rohit Bhardwaj is a Director of Architecture working at Salesforce. Rohit has extensive experience architecting multi-tenant cloud-native solutions in Resilient Microservices Service-Oriented architectures using AWS Stack. In addition, Rohit has a proven ability in designing solutions and executing and delivering transformational programs that reduce costs and increase efficiencies.
As a trusted advisor, leader, and collaborator, Rohit applies problem resolution, analytical, and operational skills to all initiatives and develops strategic requirements and solution analysis through all stages of the project life cycle and product readiness to execution.
Rohit excels in designing scalable cloud microservice architectures using Spring Boot and Netflix OSS technologies using AWS and Google clouds. As a Security Ninja, Rohit looks for ways to resolve application security vulnerabilities using ethical hacking and threat modeling. Rohit is excited about architecting cloud technologies using Dockers, REDIS, NGINX, RightScale, RabbitMQ, Apigee, Azul Zing, Actuate BIRT reporting, Chef, Splunk, Rest-Assured, SoapUI, Dynatrace, and EnterpriseDB. In addition, Rohit has developed lambda architecture solutions using Apache Spark, Cassandra, and Camel for real-time analytics and integration projects.
Rohit has done MBA from Babson College in Corporate Entrepreneurship, Masters in Computer Science from Boston University and Harvard University. Rohit is a regular speaker at No Fluff Just Stuff, UberConf, RichWeb, GIDS, and other international conferences.
Rohit loves to connect on http://www.productivecloudinnovation.com.
http://linkedin.com/in/rohit-bhardwaj-cloud or using Twitter at rbhardwaj1.