Skip to main content
This domain is for sale. Contact Snagged to learn more.
TE

Give your coding agent independent proof that its web and mobile app works.

Testsy is an AI testing service for websites and iOS or Android apps built by coding agents. It runs defined user flows on selected devices or browsers, reports failed checks with evidence, and returns a fix prompt your agent can use.

Agenticness = how independently a tool can take action, scored across 9 dimensions. Scored by Agentic.ai on our published 36-point rubric. Rubric and rules by David Kooi, Skylark Creations. See full rubric → Last re-evaluated 20 November 2026.

See pricing ↓

Web
iOS
Vision
B2B
Computer Use
MCP Support
Cloud Hosted
Visit Testsy

Is this your tool? Claim this listing to manage your content and analytics.

Ask about Testsy

Get answers based on Testsy's actual documentation

Try asking:

About

What It Is

Testsy is an agent-oriented end-to-end testing tool for developers building web and mobile software with AI coding agents. It independently exercises a website in Chrome or an iOS/Android app on a chosen device and OS version, then evaluates whether visible requirements passed.

What to Know

Testsy is most useful as a verification layer after an AI agent changes an application: it can catch regressions that a coding agent's own assertion that a feature works would miss. Its results are concrete, showing the expected and observed values,...

Key Features
Connects to Claude Code, Cursor, Codex, Gemini CLI, and other MCP clients through an MCP endpoint
Plans test scenarios from natural-language requirements with ordered steps and visible pass checks
Runs website tests in Chrome
Tests iPhone, iPad, and Android apps on selected OS versions
Runs individual tests or an entire project test suite through MCP
Use Cases
Verify that a newly implemented sign-up flow sends a confirmation email and opens the dashboard correctly
Run an iOS test that changes an app setting and confirms the updated value appears on the home screen
Test an Android APK through a saved flow before handing a build to QA
Agenticness: Adaptive Collaborator

Proposes and executes multi-step plans with your approval.

High evidence
Last evaluated: Nov 20, 2026

Dimension Breakdown

Action Capability
Autonomy
Planning
Adaptation
State & Memory
Reliability
Interoperability
Safety
Operator Sovereignty

Categories

Pricing
  • Free: 10 free runs with no card for the displayed first-test flow.
Details
AddedNovember 20, 2026
RefreshedNovember 20, 2026
Quick Facts
DeploymentCloud-hosted
AutonomySemi-autonomous
Model supportMulti-model
Open sourceNo
MCP supportYes
Team supportSmall team
Pricing modelFreemium
Interfacegui, api
Sources
Last updated November 20, 2026
Newsletter

Join the Agentic AI Insider.

I use AI for: