Coval
Coval is a simulation and evaluation platform for AI voice and chat agents. Inspired by autonomous-vehicle testing, it simulates end customers across realistic scenarios, personas, accents, and background noise, then scores agent behavior with built-in and custom metrics. The REST API manages agents, test sets and test cases, personas, metrics, simulation runs, and production conversations.
Coval publishes 12 APIs on the APIs.io network, including Agents API, Conversations API, Metrics API, and 9 more. Tagged areas include AI, Agents, Voice AI, Simulation, and Evaluation.
Coval’s developer surface includes authentication, documentation, engineering blog, and 8 more developer resources.
Kin Score
APIs 12
Individual APIs this provider publishes, each with its own machine-readable definition.
Coval Agents API
Connect and manage AI agents under test.
Coval Conversations API
Submit and evaluate production conversations.
Coval Metrics API
Define scoring criteria, thresholds, and baselines.
Coval Mutations API
Manage agent configuration variants (mutations).
Coval Personas API
Configure simulated callers, voices, and scenario behavior.
Coval Reports API
Create and manage evaluation reports.
Coval Run Templates API
Save reusable run configurations.
Coval Runs API
Launch and manage simulation runs.
Coval Scheduled Runs API
Schedule recurring simulation runs.
Coval Simulations API
Inspect individual simulation results.
Coval Test Cases API
Manage individual evaluation inputs within a test set.
Coval Test Sets API
Manage collections of test cases (datasets).
Scroll for all 12
Open Collections 1
Open, tool-agnostic API collections (OpenAPI-derived and Bruno).
Coval API
OPEN COLLECTIONPricing Plans 1
Published pricing tiers and plan structures.
Rate Limits 1
Documented rate limits and quota policies.
Coval Ai Rate Limits
RATE LIMITSFinOps 1
Cost, billing, and metering signals for API financial operations.
Coval Ai Finops
FINOPSSecurity Posture 2
Authentication, domain security, vulnerability disclosure, and trust-center signals.
Agentic Access 1
Recommended x-agentic-access execution contracts for AI agents.
Resources
Documentation 1
Reference material describing how the API behaves
Agent Surfaces 1
MCP servers, agent skills, and machine-readable catalogs
Build 1
SDKs, sample code, and the tooling you integrate with
Access & Security 2
Authentication, authorization, and security posture
Operate 1
Status, limits, changes, and where to get help
Commercial 2
Pricing, plans, and the legal terms of use
Company 3
The organization behind the API