HyperHack-2024 - SimplifyExtraction
Use Case Description
Web extraction tasks require human effort to define the selectors during design time, and to monitor the selectors during runtime. Effort required to define selectors to navigate websites is significant and require developer expertise. Frequent changes in website layouts cause automations to fail and require constant monitoring.
Solution: Create an LLM-based web extractor which generates the selectors (XPaths) to identify elements on a page based on user prompts and descriptions. A multi-agent extractor using a UiPath State Machine, inspired by LangGraph, results in better performance as an extractor agent and a reviewer agent work together to define the best selectors for any page.
AS-IS WORKFLOW, TO-BE WORKFLOW
Other information about the use case
Industry categories for this use case: Information Technology and Services
Skill level required: Advanced
UiPath Products that were used: UiPath Studio
Other applications that were used: Integration Service, Azure OpenAI
Other resources: -
What is the top ROI driver for this use case?: Accelerate growth and operational efficiency
ashokkarale
Yoichi
singh_sumit
sven.wullum1
adi.mehare
ppr
sonaliaggarwal47
shahidh.aqeel.shahul
Akash_Javalekar1
Sami_Rajput