Eval directory
Evals for Decagon
4 evaluation packs covering adversarial robustness, safety gates, workflow quality, and operator-level checks for Decagon AI products.
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.
How complete this published benchmark library is across datasets, metrics, rubrics, use-case maps, and pack context. This is library coverage, not an agent performance score.
Test datasets
4/4 packs
Scoring metrics
4/4 packs
Judge rubrics
4/4 packs
Use-case maps
0/4 packs
Pack context
4/4 packs
Available eval packs for Decagon
4 packs ready to run.
Conversational Quality Resolution Accuracy
CorrectnessTask CompletionTool Selection61 graded scenarios covering edge cases, failure modes, and quality checks.
Deflection Vs Escalation Decisioning
Task CompletionTool Selection66 graded scenarios covering edge cases, failure modes, and quality checks.
Tool Use Precision Recall Against Connected Systems
Task CompletionKnowledge RetentionTool Selection60 graded scenarios covering edge cases, failure modes, and quality checks.
Transactional High Risk Action Safety
Task CompletionTool Selection54 graded scenarios covering edge cases, failure modes, and quality checks.
Why eval Decagon AI
Decagon's AI features ship behind brand promises about accuracy, safety, and reliability. Buyers and integrators need to know those promises hold up under adversarial prompts, edge-case workflows, and the long tail of real customer inputs — not just the demo path.
The Corsac eval library for Decagon measures four dimensions teams care about most when deploying customer support agents:
- Adversarial robustness — does the agent resist prompt injection, jailbreaks, and social-engineering attempts?
- Workflow quality— does it complete the task buyers were shown in the demo, on inputs that don't look like the demo?
- Safety gates — does it escalate or refuse when it should, and only then?
- Operator quality — does it preserve analyst trust by surfacing the right context at the right time?
Every eval pack above is hand-authored against Decagon's public product surface and runnable in Corsac with your own data.