Your AI Wrote the Code. Now What?
summary
AskUI runs a single CSV test suite concurrently across an Android Automotive head unit via ADB, an Android tablet HMI, and a paired iOS companion app without Espresso or XCUITest by using screenshots-only agents that observe screens, decide actions with a VLM/LLM, and trigger input via ADB or a companion client/hardware. Tests self-heal with system prompts, produce detailed pass/fail reports and agent traces, scale to 4,000 tests overnight, and support on‑prem models and air‑gapped deployments.
AI-written summary · about
chapters (6)
- 0:00AI testing challenges
- 1:47Traditional test automation fails
- 3:54LLM-based testing systems
- 5:16Live demo: AI device testing
- 13:02System prompts for AI agents
- 16:09Q&A
related talks
19mQA Agents for Android: How AI Is Changing the Game in Testing
35mApp Testing with AI Tools – Make it Easy
18mHow AI Can Act as Top Layer of Appium Automation Runs
34mThe Era of AI Agents for Device Control: Challenges in Android UI/E2E Testing Using mobile-mcp
37mNo More Writing Test Code: Auto Designing and Generating Asynchronous Tests with JetBrains AI Assistant
43mUI testing is so easy - said no developer ever
55mAI-First Testing
11mDragonCrawl: Revolutionizing Mobile Testing with GenAI