Sift
An AI-integrated open source platform for seamless search and collaboration with forest restoration practitioners.
2x
Reducing the document and research paper review time
3000
Research papers have been currently trained for the LLM
Overview
Consisting of 2,400 members, including volunteers, scientists, engineers, Collaborative Earth is a non-profit organization which operate in various ecological regeneration labs to create pathways for social and ecological regeneration.
Team
Product Designers, Organization Lead, Data Scientists and Mentors
Company
Collaborative Earth
role
0-1 - UX Design - Product Strategy - Design Systems
Role
I designed a 0–1 web platform, conducting research and usability testing with participants across the globe, synthesizing insights, defining user flows and interactions. Created a design system to maintain a cohesive visual language.
problem
Sifting through sparse information is a challenge for forest regeneration practitioners
We received a brief from Collaborative Earth with the mission to review and synthesize data due to the abundance of unpublished research, documents, and case studies, some of which are in non-English formats.
Evidence from the team
Solution
AI-integrated open-source platform for forest restorations, enabling quicker review of research papers.
The project resulted in an open-source repository that uses artificial intelligence to enhance planning and collaboration by providing insights, community knowledge, resources, and mapping tools.
how we approached
solution sneak peek
Multi search engine
Implementation of a dual search function, giving users to both search and quickly extract insights by uploading research papers or policy documents. AI-powered search is an advanced search bar helps them to find relevant and well-cited sources
Collaboration
The collections enable collaboration among team members and organizations, where they ca track the types of resources saved, the number of files stored, and the count of participating members.
Customize tags
Practitioners can create their personal space, using customized tags as organizers for clear tagging and labeling when saving resources.
Smart insights
Smart insights are generated through LLMs analyzing thousands of vetted resources, the tool produces concise summaries, making it easier for practitioners to review the material quickly.
synthesis from research
What could we make better, and what was missing?
We conducted primary research on the contents of gray literature, exploring their current data usage and methods, and distilled our findings as follows.
how we approached
Overlooked metrics on tools and community impact
Practitioners tend to look for certain tools and resources. Metrics like income and well-being of local communities are often overlooked, but crucial for project success.
Lack of universal tool
There is a lack of one universal tool that aggregates key features for restoration practitioners.
Challenges in quick literature scanning and documentation
It is challenging for practitioners to efficiently scan literature, in short time periods.
synthesis from research
Using the insights, we brainstormed ideas centered on information accuracy and progress tracking for volunteers and practitioners, generating four distinct directions.
What didn't work out as expected?
