DragonCrawl: A Generative, Intent-Based Framework for Scalable Mobile End-to-End Testing
Source
Sowjanya Puligadda, Mengdie Zhang, Ali Zamani, Dhruva Dixith Kurra, Eric Chen, Juan Marcano
Author
Sowjanya Puligadda, Mengdie Zhang, Ali Zamani, Dhruva Dixith Kurra, Eric Chen, Juan Marcano
Date
Key takeaways · AI-distilled
DragonCrawl targets regression, not exploration: it validates specific user flows on every code change and blocks commits that break critical functionality - 91.6% pass on iOS and 92.2% on Android across 1,013 tests in CI.
The economics are the headline: test onboarding drops from 96-120 hours to under 4, with an estimated 27 developer-years saved in maintenance.
Architecture evolved from V1 embeddingA list of numbers representing a piece of text's meaning, so that similar meanings end up numerically close and can be searched.Full definition →-similarity matching to V2 generative intent-based reasoning with GPT-4o multimodalA model that works with more than text — reading images, audio, or video, and sometimes generating them too.Full definition → - vision handles end-state detection while tool calls bridge backend state transitions.
Production lessons include fighting token explosion and memory constraints - the operational half most LLMA large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.Full definition →-testing papers skip.
Terms in this piece · Glossary
embedding — A list of numbers representing a piece of text's meaning, so that similar meanings end up numerically close and can be searched.
benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
multimodal — A model that works with more than text — reading images, audio, or video, and sometimes generating them too.
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
Why it matters
Shows a validated production path for replacing brittle UI-selector mobile tests with GPT-4o-driven intent reasoning, with real numbers on pass rates and engineering time saved that practitioners can benchmarkA standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.Full definition → against.
Key quotes
“DragonCrawl validates specific user flows on every code change, blocking commits that break critical functionality.”
“The system reduces test onboarding time from 96-120 hours to under 4 hours and has saved an estimated 27 developer years in test maintenance effort.”
