Show HN: Finalrun – Spec-driven testing using English and vision for mobile apps
Vision-based AI testing that syncs with your codebase. No more brittle selectors.
Why it matters
A developer has open-sourced a spec-driven testing tool that uses vision-based AI agents to test mobile apps in plain English, solving the sync problem between test flows and evolving codebases—relevant to teams automating QA and reducing testing maintenance overhead.
The key facts
11 to knowVision-based execution across Android and iOS
YAML-based test flow specification
Test generation directly from codebase context via MCP
Open-source release with core components available
Eliminates XPath/accessibility ID selectors in favor of AI vision understanding
Published on HackerNews with 14 points and 4 comments
Test generation from codebase context via MCP
YAML-based test flow definition
Solves test-code drift problem by keeping tests alongside codebase
Demo shows AI-built feature + auto-generated vision-based test execution
Open-sourced core components on GitHub
Go to the source
Hacker Newsgithub.com
Publisher excerpt: I wanted to test mobile apps in plain English instead of relying on brittle selectors like XPath or accessibility IDs. With a vision-based agent, that part actually works well. It can look at the screen, understand intent, and perform actions across Android and iOS. The bigger problem showed up…