Skip to main content
Kuldeep Singh
Kuldeep SinghDigital Architecture
SALESFORCE · AGENTIC AI · MULTI-AGENT ORCHESTRATIONRole: Principal AI & Platform Architect

DAISY — Entity Scoring & Agent Orchestration

The hard problem is not adding an agent. It is deciding which agent, skill and tool should act next.

The hard problem is not adding an agent. It is deciding which agent, skill and tool should act next.

ORCHESTRATORENTITY SCORINGTOOL CALLINGMULTI-AGENT
01 // The Constraint

What Made the Problem Difficult

Enterprise Salesforce environments coordinate complex, high-stakes business operations spanning quoting approvals, customer service escalations, provisioning workflows, and contract reconciliations. Incorporating LLM intelligence into these mission-critical domains required deterministic control.

Core Platform Constraint

Single-agent LLM architectures fail in enterprise CRM contexts. They suffer from context window pollution, unpredictable tool execution, hallucinations during complex workflows, and an inability to assess whether a business entity is ready for automated intervention.

Boundary Invariants & Operational Limits:
  • !Prevent unconstrained or hallucinatory agent mutations on sensitive enterprise CRM records
  • !Routing and agent delegation must be auditable, transparent, and grounded in deterministic entity scoring
  • !Zero execution of mutating actions without strict JSON schema validation and permission enforcement
  • !Isolate context windows across specialized functional domains to prevent prompt bloat and cross-task degradation
  • !Architect custom orchestration on top of Salesforce capabilities rather than relying on black-box chat bots
02 // The Architecture

What System Was Designed

Engineered DAISY as a custom Salesforce orchestrator agent topology. Ingress requests and CRM entity states pass through a three-stage pipeline: 1) Entity Scoring evaluates data completeness, urgency, and operational risk; 2) Dynamic Multi-Agent Routing selects the ideal specialized subordinate agent with an isolated context window; 3) Governed Tool-Calling executes validated skill schemas against Salesforce enterprise capabilities with comprehensive audit envelopes.

03 // The Key Decision

Pivotal Architectural Choices

Key Architectural Decisions

ADR // 01DETERMINISTIC CHOICE

Score-First Triage Model vs. Immediate LLM Generation

Context:

Invoking LLMs on incomplete or invalid CRM entities wastes tokens and invites hallucinated actions.

Alternatives Evaluated:
  • Prompt LLM directly on raw record payload
  • Static hardcoded rule triggers without AI capabilities
Chosen: Deterministic entity scoring pipeline evaluating record state prior to agent invocation.

Ensures agents only act on entities that meet strict data readiness criteria, minimizing expensive model calls and eliminating garbage-in, garbage-out execution.

ADR // 02DETERMINISTIC CHOICE

Hierarchical Multi-Agent Topology vs. Monolithic All-in-One Prompt

Context:

A single agent trying to understand quoting rules, service SLAs, and billing policies inevitably suffers context degradation.

Alternatives Evaluated:
  • Mega-prompt system instruction with 30+ tools
  • Autonomous uncoordinated agent swarms
Chosen: Central DAISY orchestrator routing to narrow, task-specialized sub-agents.

Confines context windows to specific domains, ensuring precise tool calling and complete architectural observability.

04 // The Engineering

What Was Actually Built

01

Constructed a deterministic entity scoring engine evaluating CRM record completeness, priority tiers, and risk factors.

02

Engineered an intent classification router delegating qualified requests to specialized subordinate agents.

03

Implemented a strictly typed JSON Schema tool registry defining parameter boundaries for every Salesforce platform action.

04

Built an enterprise governance envelope capturing structured audit trails of scores, routing decisions, and tool outputs.

05

Designed context isolation mechanisms that instantiate fresh, focused prompt environments per delegated task.

05 // The Trade-offs

Deliberate Architectural Compromises

Trade-offs & Mitigations

Multi-Hop Orchestration Latency vs Operational Safety

Architectural Benefit:

Deterministic guardrails, audit visibility, and elimination of runaway tool execution.

Associated Cost:

Slight incremental latency incurred during orchestrator scoring and routing hops.

Mitigation Strategy:

Pre-computed scoring vectors and optimized parallel skill evaluation.

Declarative Schema Tool Gates vs Freeform Autonomous Actions

Architectural Benefit:

Absolute guarantee that database mutations comply with platform validation rules and governor limits.

Associated Cost:

Every capability requires formal JSON schema specification and parameter mapping.

Mitigation Strategy:

Created standardized tool scaffolding templates and reusable skill modules.

06 // The Result

Verified Outcomes

✓ VERIFIED RESULT

Successfully orchestrated multi-agent workflows across complex Salesforce business entities

✓ VERIFIED RESULT

Eliminated hallucinated platform mutations by enforcing strict JSON schema gates at the tool boundary

✓ VERIFIED RESULT

Established full audit traceability for every scoring decision, agent handoff, and tool invocation

✓ VERIFIED RESULTRequires Benchmark Confirmation

Scoring accuracy, agent latency, and transaction volume benchmarks: [VERIFY WITH KULDEEP]

07 // Architecture Blueprint

System Schematic & Data Flow

System Topology Blueprint
DAISY Custom Orchestrator & Multi-Agent Routing Topology
INTERACTIVE SCHEMATIC
ROOT AGENT · CENTRAL GOVERNANCEDAISY Custom Orchestrator AgentDeterministic triage & context boundary isolation01 · Entity ScoringUrgency, completeness, risk02 · Dynamic RoutingIntent & capability matcher03 · Context BoundaryIsolated prompt scopesSPECIALIZED AGENT RUNTIMES · NARROW TOOL BINDINGSAgent A: Quoting & PricingAgent B: Service EscalationAgent C: Validation & AuditGOVERNED SALESFORCE ENTERPRISE CAPABILITIESSchema-Enforced Tool Calling · Composite API Mutations · Audit Telemetry Envelopes
SCORE-FIRST TRIAGEEvaluates business entity readiness before any LLM execution or tool dispatch occurs.
ISOLATED CONTEXTSNarrow agent contexts prevent prompt degradation and cross-domain hallucinations.
STRICT SCHEMA GATESEvery tool skill verifies typed JSON payloads before touching Salesforce CRM records.

DAISY evaluates entity scores, isolates context boundaries, routes to specialized subordinate agents, and governs tool execution against Salesforce capabilities.

Text alternative for screen readers: Architecture flow: CRM Entity Ingress to DAISY Orchestrator via State & Context Ingestion; DAISY Orchestrator to Entity Scoring & Routing via Triage & Capability Matching; Entity Scoring & Routing to Specialized Agents (A/B/C) via Isolated Context Delegation; Specialized Agents to Salesforce Platform Core via Schema-Enforced Tool Execution

08 // Why It Matters

Architectural Conclusion

Agent architecture becomes interesting when orchestration, skills, routing and tool execution become first-class system concerns.

Key Lessons for Platform Scale:
  • Enterprise AI requires software architecture, not prompt improvisation. Treating scoring, routing, and tool calling as disciplined systems ensures reliability at enterprise scale.
  • A central orchestrator governing modular specialized agents provides the ultimate balance between autonomy and corporate governance.