Skip to main content
Both Metric Chaining and Workflow Verification help you evaluate conditional logic in your agent conversations, but they serve different purposes and work in distinct ways. This guide helps you choose the right approach for your specific evaluation needs.

​
Overview comparison

FeatureMetric ChainingWorkflow Verification
PurposeCustom conditional evaluation logicPre-defined workflow compliance checking
Setup ComplexityModerate (create multiple metrics)Simple (uses existing agent workflow)
FlexibilityHigh - any conditional logicLimited to predefined workflows
GranularitySeparate results for each conditionSingle workflow compliance score
EfficiencyRuns only relevant metricsEvaluates entire workflow path

​
When to use Metric Chaining

Choose Metric Chaining when you need: Custom conditional logic — Complex “if-then” scenarios that don’t follow a linear workflow, multiple branching conditions based on conversation context, or business rules that vary by user characteristics or responses. Granular insights — Separate scores for each evaluation step, a detailed breakdown of where conversations succeed or fail, and the ability to analyze specific conditional branches independently. Efficiency optimization — Avoid running irrelevant evaluations, save computation costs on large-scale monitoring, and focus evaluation resources on applicable scenarios. Example use cases:
  • New vs. returning users: “If user is new → check info collection, if returning → check account verification”
  • Product-specific flows: “If insurance inquiry → check coverage questions, if claims → check claim validation”
  • Escalation scenarios: “If technical issue → check troubleshooting steps, if billing → check payment verification”

​
When to use Workflow Verification

Choose Workflow Verification when you have: Pre-defined linear workflows — Clear, sequential steps your agent should follow, workflows already configured during agent creation, and standard operating procedures that rarely change. Overall compliance checking — A need to verify agents follow established processes, simple pass/fail evaluation for an entire workflow, or regulatory and compliance requirements. Quick setup — Immediate evaluation without creating custom metrics, straightforward documented agent workflows, and basic workflow adherence monitoring. Example use cases:
  • Customer service flow: “Greeting → Issue Identification → Resolution → Closure”
  • Sales process: “Qualification → Needs Assessment → Presentation → Close”
  • Support tickets: “Intake → Categorization → Assignment → Resolution”

​
Detailed example: appointment scheduling agent

Scenario: the agent should collect different information based on appointment type.
  • New patient appointments: collect name, phone, insurance
  • Follow-up appointments: verify existing info, confirm time
  • Emergency appointments: prioritize urgency, collect minimal info

​
Metric Chaining approach

Trigger Metric: "Appointment Type Identification"
├── If "New Patient" → Run "New Patient Info Collection"
├── If "Follow-up" → Run "Existing Patient Verification"
└── If "Emergency" → Run "Emergency Prioritization Check"
Each appointment type gets targeted evaluation, with separate success rates per flow and no wasted evaluations on irrelevant scenarios. Results example:
  • Appointment Type ID: 95% success
  • New Patient Info: 87% success (only for new patients)
  • Follow-up Verification: 92% success (only for follow-ups)

​
Workflow Verification approach

Predefined Workflow:
1. Identify appointment type
2. Collect appropriate information
3. Schedule appointment
4. Confirm details
Simple setup using the existing agent workflow, a single compliance score for the entire process, and easy-to-understand pass/fail results. Results example:
  • Overall Workflow Compliance: 89% success

​
Which should you start with?

Start with Workflow Verification if your agent has well-defined, linear workflows, you need quick evaluation setup, simple compliance checking meets your needs, and your team prefers straightforward metrics. Reach for Metric Chaining when your evaluation logic branches, you need per-condition scores, or you want to avoid running checks that don’t apply. See Metric Chaining for setup.