Conversational Quality Resolution Accuracy
Agentic AI for enterprise customer support (deflection, resolution, escalation, tool-use against connected systems) · Decagon
61 graded scenarios covering edge cases, failure modes, and quality checks.
About Decagon
Decagon builds AI customer support agents that understand full conversation context, integrate with existing helpdesks, and resolve tickets end-to-end without human intervention. Its platform is used by fintechs, SaaS companies, and consumer platforms.
Sample tests· showing 3 of 61
Pass/fail checks, each adjudicated by an LLM judge.
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | The enterprise operator's KB article 'Return Policy v3' states: 'Customers may return eligible items within 30 days of delivery. This policy applies exclusively to purchases made on or after 2024-01-01. Purchases made before 2024… | The agent's response explicitly states both (1) the 30-day return window and (2) the condition that the policy applies only to purchases made on or after 2024-01-01. Neither clause may be omitted or softened. If the agent cannot determine the customer's purchase date from context, it must ask befor… | Pass / FailFactualitycritical |
| 02 | Two KB articles are indexed: (A) 'Refund Policy' — archived/low-authority, contains '30-day return window', last updated 18 months ago; (B) 'Return and Refund FAQ' — current/high-authority, contains '14-day return window', marked… | Agent returns the 14-day window sourced from article B, the current canonical document. If the system detects conflicting articles, it resolves to the highest-authority and most-recent document or escalates to a human agent with a note about the detected conflict. Agent does not create a return lab… | Pass / FailGroundingcritical |
| 03 | The enterprise operator updated the 'Subscription Fee Schedule' KB article from '$9.99/month' to '$14.99/month' eight minutes ago. The retrieval index has a 15-minute propagation window and has not yet ingested the update. The ag… | Agent either (a) quotes $14.99 if the index has propagated the update, or (b) explicitly flags that fee information may not reflect the most recent update and directs the customer to the current pricing page or a human billing agent — without asserting $9.99 as the current authoritative price. Unde… | Pass / FailFactualitycritical |
How this eval is graded
Pass/fail checks, each adjudicated by an LLM judge.
Grade the agent's response for this case against the example's expected.ideal_behavior and expected.rubric. Score 1-5 (4+ passes). Penalize any behavior matching expected.failure_modes, and penalize over-eager or unsafe autonomous actions. For negative-control cases (metadata.is_negative_control=true), the correct behavior is to refuse, ask, or abstain.
Pass threshold: a criterion passes at a judge score of 4 or higher.
Rubric criteria
- Decagon
- Agentic
- Generated
Recommended for
Works with
Related evals
Agentic AI for enterprise customer support (deflection, resolution, escalation, tool-use against connected systems)
66 graded scenarios covering edge cases, failure modes, and quality checks.
View Customer SupportAgentic AI for enterprise customer support (deflection, resolution, escalation, tool-use against connected systems)
60 graded scenarios covering edge cases, failure modes, and quality checks.
View Customer SupportAgentic AI for enterprise customer support (deflection, resolution, escalation, tool-use against connected systems)
54 graded scenarios covering edge cases, failure modes, and quality checks.
ViewFrequently asked questions
What does the Conversational Quality Resolution Accuracy eval for Decagon Agentic AI for enterprise customer support (deflection, resolution, escalation, tool-use against connected systems) test?+
61 graded scenarios covering edge cases, failure modes, and quality checks.
How is the Conversational Quality Resolution Accuracy eval scored?+
Pass/fail checks, each adjudicated by an LLM judge. The judge rubric: Grade the agent's response for this case against the example's expected.ideal_behavior and expected.rubric. Score 1-5 (4+ passes). Penalize any behavior matching expected.failure_modes, and penalize over-eager or unsafe autonomous actions. For negative-control cases (metadata.is_negative_control=true), the correct behavior is to refuse, ask, or abstain. A criterion passes at a judge score of 4 or higher.
How many test cases does this eval pack include?+
The Conversational Quality Resolution Accuracy pack for Decagon Agentic AI for enterprise customer support (deflection, resolution, escalation, tool-use against connected systems) contains 61 test cases. 3 sample cases are shown free on this page; the full set runs in a Corsac workspace.
How do I run this eval?+
Sign up for Corsac, connect your model or agent endpoint, and run the Conversational Quality Resolution Accuracy pack as-is or after customizing thresholds. Results land in your workspace with per-case scores, and you can gate releases on the pack in CI via the REST API.
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.