![[The AI Show Episode 142]: ChatGPT’s New Image Generator, Studio Ghibli Craze and Backlash, Gemini 2.5, OpenAI Academy, 4o Updates, Vibe Marketing & xAI Acquires X](https://www.marketingaiinstitute.com/hubfs/ep%20142%20cover.png)
![[DEALS] The Premium Learn to Code Certification Bundle (97% off) & Other Deals Up To 98% Off – Offers End Soon!](https://www.javacodegeeks.com/wp-content/uploads/2012/12/jcg-logo.jpg){kind=logo}
![From drop-out to software architect with Jason Lengstorf [Podcast #167]](https://cdn.hashnode.com/res/hashnode/image/upload/v1743796461357/f3d19cd7-e6f5-4d7c-8bfc-eb974bc8da68.png?#)
.png?#)
.webp?#)
_Christophe_Coat_Alamy.jpg?#)
 (1).webp?#)
![Apple Considers Delaying Smart Home Hub Until 2026 [Gurman]](https://www.iclarified.com/images/news/96946/96946/96946-640.jpg)
![iPhone 17 Pro Won't Feature Two-Toned Back [Gurman]](https://www.iclarified.com/images/news/96944/96944/96944-640.jpg)
![Tariffs Threaten Apple's $999 iPhone Price Point in the U.S. [Gurman]](https://www.iclarified.com/images/news/96943/96943/96943-640.jpg)
Stage Conclusion: UI-Tars + RAG = A New Approach for Automated E2E & Exploratory Testing (Part 3)
Articles in this series: Articles in this series: Part 1 - Practical Applications of AI in Test Automation — Context, Demo with UI-Tars LLM & Midscene Part 2 - Data: UI-Tars VS GPT-4o in Midscene Part 3 - Stage Conclusion: UI-Tars + RAG = A New Approach for Automated E2E & Exploratory Testing This is the final article in this series - I will present an example demonstrating: How to integrate UI-Tars' system-reasoning 2 with our locally built RAG using Ollama and LangChain to create a system that understands high-level user instructions and automates execution based on browser screenshots at each stage. Verify the capability of system-2 reasoning after combining the UI-Tars & local RAG 1. End-to-End Demo This Demo uses Miro as an example to demonstrate the capability to handle a non-B2C & complicate system, the AI Agent follows a single user's instruction: "Create a new board with 2 sticky notes and link these 2 sticky notes by a line. " ⚠️VERY IMPORTANT⚠️: The Demo uses Miro's Free Plan, which is allowed for everyone. The test is executed less than 10 times, to verify the stability. The authentication part uses my personal Miro Free account(hardcoded already to avoid any other risks), I strongly ask any readers who want to reproduce this test for any customer-facing products should NOT impact the normal usage of the product, and MUST follow up the policy of the product respectively. (
Articles in this series:
Articles in this series:
- Part 1 - Practical Applications of AI in Test Automation — Context, Demo with UI-Tars LLM & Midscene
- Part 2 - Data: UI-Tars VS GPT-4o in Midscene
- Part 3 - Stage Conclusion: UI-Tars + RAG = A New Approach for Automated E2E & Exploratory Testing
This is the final article in this series -
I will present an example demonstrating:
- How to integrate UI-Tars' system-reasoning 2 with our locally built RAG using Ollama and LangChain to create a system that understands high-level user instructions and automates execution based on browser screenshots at each stage.
- Verify the capability of
system-2 reasoningafter combining theUI-Tars& localRAG
1. End-to-End Demo
This Demo uses Miro as an example to demonstrate the capability to handle a non-B2C & complicate system, the AI Agent follows a single user's instruction: "Create a new board with 2 sticky notes and link these 2 sticky notes by a line. "
⚠️VERY IMPORTANT⚠️: The Demo uses Miro's Free Plan, which is allowed for everyone. The test is executed less than 10 times, to verify the stability. The authentication part uses my personal Miro Free account(hardcoded already to avoid any other risks), I strongly ask any readers who want to reproduce this test for any customer-facing products should NOT impact the normal usage of the product, and MUST follow up the policy of the product respectively.
(
