AustraliaEducation2024 – ongoingLa Trobe University
Retrieval-augmented research assistant on autism papers with watsonx
La Trobe researchers develop the AI component of an autism-research prototype in under a week
Problem
Researchers wanted faster access to university-approved knowledge on autism. Outsourcing such a tool was costly and slow.
Approach
The team built a retrieval-augmented proof of concept on IBM Watson Discovery, watsonx Assistant and watsonx.ai, drawing on over 100 autism papers. A co-designed application showed researchers how to turn data into market-ready products.
Results
Takeaway
The researchers developed the prototype's AI component in less than a week. IBM reports an 8.7x cost saving from building in-house compared with outsourcing.
Categories
- Size
- Large enterprise
- Industry
- Education
- Business function
- IT and R&DInternal work and knowledge management
- Innovation type
- Process innovation
- AI technology
- Generative AIConversational and voice AI
- Adoption
- Vendor solution
- Evidence
- Vendor's case study
Sources
Source summaries
IBM describes a watsonx proof of concept built by La Trobe researchers on over 100 autism papers. It reports cost and development-time savings.
Full details are in the original sources.
