Converge Domain

Domain-specific agent implementations and business use cases for the Converge runtime.

Website: converge.zone | Docs: docs.rs | Crates.io: converge-domain

Installation

[dependencies]
converge-domain = "0.2"

Related Crates

Crate	Version	Description
converge-core	0.6.1	Runtime engine, agent traits, capabilities
converge-provider	0.2.3	14+ LLM providers, model selection
converge-domain	0.2.3	12 business use cases

Use Cases

Business Strategy

Use Case	Module	Description
Growth Strategy	`growth_strategy`	Market signal analysis, competitor intelligence, strategy evaluation
Strategic Sourcing	`strategic_sourcing`	Vendor assessment, risk scoring, negotiation recommendations
SDR Sales	`sdr_sales`	Sales qualification funnel, lead scoring

Operations

Use Case	Module	Description
Supply Chain	`supply_chain`	Multi-warehouse routing, demand forecasting, cost optimization
Inventory Rebalancing	`inventory_rebalancing`	Cross-region transfers, financial impact analysis
Resource Routing	`resource_routing`	Task-resource matching, constraint satisfaction

Enterprise

Use Case	Module	Description
Meeting Scheduler	`meeting_scheduler`	Multi-participant availability, timezone normalization, conflict resolution
Release Readiness	`release_readiness`	Quality gates, risk assessment, go/no-go decisions
Compliance Monitoring	`compliance_monitoring`	Regulation parsing, violation detection, remediation proposals
HR Policy Alignment	`hr_policy_alignment`	Policy distribution, understanding signals, compliance tracking

Data & CRM

Use Case	Module	Description
Catalog Enrichment	`catalog_enrichment`	Product deduplication, schema validation, feed ingestion
CRM Account Health	`crm_account_health`	Churn risk scoring, upsell identification, action prioritization

Architecture Patterns

Each use case demonstrates:

Fan-out/fan-in — Parallel data collection → consolidated analysis
Pipeline stages — Seeds → Signals → Hypotheses → Strategies → Evaluations
Invariant enforcement — Domain-specific quality gates (Gherkin-style)
Idempotency — Context-based deduplication, not hidden state

Deterministic + LLM Variants

Each use case includes two implementations:

Variant	Module Suffix	Description
Deterministic	(base)	Rule-based, fully reproducible
LLM-enhanced	`_llm`	AI-powered analysis with structured output

// Deterministic version
use converge_domain::growth_strategy::StrategyAgent;

// LLM-enhanced version
use converge_domain::growth_strategy_llm::StrategyAgentLlm;

Quick Start

use converge_core::{Engine, Context, ContextKey, Fact};
use converge_domain::growth_strategy::{
    MarketSignalAgent, CompetitorAgent, StrategyAgent, EvaluationAgent
};

// Create engine with domain agents
let mut engine = Engine::new();
engine.register(MarketSignalAgent);
engine.register(CompetitorAgent);
engine.register(StrategyAgent);
engine.register(EvaluationAgent);

// Seed with market data
let mut ctx = Context::new();
ctx.add_fact(Fact::new(
    ContextKey::Seeds,
    "market-data",
    "Q4 revenue: $2.3M, growth: 15% YoY"
))?;

// Run to convergence
let result = engine.run(ctx)?;

// Extract evaluated strategies
for fact in result.context.get(ContextKey::Evaluations) {
    println!("Strategy evaluation: {}", fact.content);
}

Domain Evals

The crate includes a domain-level evaluation framework for testing use case quality:

use converge_domain::evals::{DomainEval, EvalAgent};

// Define domain-specific evaluation criteria
let eval = DomainEval::new("growth_strategy")
    .with_criterion("strategy_quality", |ctx| {
        // Evaluate strategy output quality
    });

Testing

# Run all domain tests
cargo test -p converge-domain

# Run specific use case tests
cargo test -p converge-domain growth_strategy

Repository

This crate is part of the Converge project.

Standalone repo: github.com/kpernyer/converge-domain

License

MIT

converge-domain 0.2.3