{"slug": "exploratory-testing-with-ai-beyond-predefined-test-cases", "title": "Exploratory Testing with AI: Beyond Predefined Test Cases", "summary": "A developer released iSimBot-MCP, an open-source tool that lets MCP-compatible AI agents such as Claude Code and Codex observe and control a local iOS Simulator for exploratory testing. The agent drives investigation through screenshots, taps, swipes, and text input, working with already-installed apps without build-pipeline integration, an in-app testing SDK, or source-code access. It requires Apple Silicon, macOS 15+, and Xcode 26+ with an iOS simulator runtime, and supports one selected simulator per server.", "body_md": "Unit tests check logic, snapshot tests detect output changes, and end-to-end tests verify predefined journeys—but unexpected behavior often appears outside those paths.\n\nExploratory testing starts with a goal, not a fixed script. Each observation informs the next action, and unexpected behavior becomes a reason to investigate further.\n\nAn AI agent with access to an app's interface can follow this loop:\n\n**Observe → act → inspect → decide what to explore next.**\n\nThe developer defines the scope. The agent chooses interactions, tries alternative paths, and documents potential issues. No predefined test flow is required.\n\n**iSimBot-MCP** is an open-source tool that lets Claude Code, Codex, and other MCP-compatible agents see and control the local iOS Simulator.\n\nIt works with apps already installed in the simulator. No build-pipeline integration, in-app testing SDK, or source-code access is needed to explore the interface.\n\nThe agent drives the investigation through screenshots, taps, swipes, and text input. Known action sequences can also return multiple screenshots in a single call.\n\n```\nbrew install wei0121/tap/isimbot-mcp\nisimbot setup\n```\n\nRequires Apple Silicon, macOS 15+, and Xcode 26+ with an iOS simulator runtime. After setup, restart the selected client, connect to the simulator, and describe what to investigate.\n\nThe tool currently supports one selected iOS simulator per server. Build automation and recurring scheduling are outside its scope.\n\nAI observations require human review: agents can miss issues or misunderstand intended behavior. Exploration complements existing tests; it does not establish that an app is bug-free.\n\n[Source code, demo, and installation instructions](https://github.com/wei0121/iSimBot-mcp)\n\nHappy for any feedback.", "url": "https://wpnews.pro/news/exploratory-testing-with-ai-beyond-predefined-test-cases", "canonical_source": "https://dev.to/wei0121/exploratory-testing-with-ai-beyond-predefined-test-cases-17np", "published_at": "2026-11-02 21:21:21+00:00", "updated_at": "2026-11-02 21:22:43.437187+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "developer-tools", "agent-protocols", "artificial-intelligence"], "entities": ["iSimBot-MCP", "Claude Code", "Codex", "Apple", "Xcode", "iOS Simulator", "wei0121"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/exploratory-testing-with-ai-beyond-predefined-test-cases", "markdown": "https://wpnews.pro/news/exploratory-testing-with-ai-beyond-predefined-test-cases.md", "text": "https://wpnews.pro/news/exploratory-testing-with-ai-beyond-predefined-test-cases.txt", "jsonld": "https://wpnews.pro/news/exploratory-testing-with-ai-beyond-predefined-test-cases.jsonld"}}