Priyam Shah

Opportunity

Forest regeneration practitioners face an overwhelming task of sifting through sparsely documented information, including unpublished data, policy documents, and case studies. By emphasizing accurate decision-making and efficient workflows, we can facilitate inter-lab collaboration for improved restoration outcomes.

Solution

Open-source repository which facilitates planning and collaboration, by leveraging AI to collate relevant resources, community knowledge and mapping tools.

Team

Anusha Thalnerkar, Kirtana Kannan, Rishma Bora, Rochelle Ardersher,
Marc O'Brien

Community Partner

Collaborative Earth ↗︎

Duration

6 months

Status

Under Development

Globally, we deforest around 10 million hectares of forest every year. That's 92212 km² – equivalent to the size of Portugal.

Collaborative Earth is a lab-driven organization that ties humanities & technology across disciplinary and cultural boundaries.

For my capstone, I partnered with Collaborative Earth to co-create pathways for social & ecological regeneration.

Theory of Change

Problem ⁉️

Forest restoration practitioners must sift through numerous research papers from various sources for each project. Gray literature, eg. essential localized knowledge, is sparsely documented.

We did a thing 💡

Designing an open-source repository that facilitates planning and collaboration, by leveraging AI to collate relevant resources, community knowledge, and tools.

Impact 🤞

By emphasizing accurate decision-making and efficient workflows, we can facilitate inter-lab collaboration for improved restoration outcomes.

Research

At a glance

co-design sessions
with practitioners

key actionable insights

649

Figjam stickies until
the 'lightbulb-idea'

Themes from stakeholders interviews

Leveraging Available Resources 📚

“There's a ton of stuff out there – but the problem is that it's scattered across different platforms!”

– Restoration Ecologist at Collaborative Earth

Drivers of Success ✅
‍
“For restoration to be successful, it should improve people’s livelihoods - primarily financial.”
‍
– Restoration Ecologist at Collaborative Earth

Overcoming Failures 💫

“Building a centralized digital tool will be really helpful for people to understand causes of project failures, and in turn stage future projects up for success.”
‍
– Restoration Lead at Collaborative Earth

We conducted affinity mapping, leading to discoveries.

Challenges

Wading through ambiguity 🌪️

Our very first asset to play around with was a rather messy Excel sheet containing data from restoration volunteers. During the early days, sensemaking took up the team's maximum bandwidth.

Envisioning a product from the ground-up 🧐

Diving head-first into a new industry with the vision to build a product meant wearing numerous hats – systems thinking, user research, and most importantly, workshop design – and it elicited a learning curve that I'm incredibly grateful for.

Product concepts

Initial (failed) concepts

CoLab AI

GPT-like AI Model

Conversational UI

❌ Upon conducting early usability tests with participants, we learned that a stand-alone AI tool felt disjointed with the resource repository.

Upload Resources

Community contribution

Impact measurement

❌ Volunteer uploads may increase the likelihood of data inaccuracies due to the absence of an information screening process.

"the iterative process"

Concepts that worked

Resource Hub

Library of relevant publications

A powerful way to find resources

Volunteer uploads may increase the likelihood of data inaccuracies due to the absence of an information screening process.

AI, but under the hood

Smart Insights & Summaries

Tool-wide integration

A deep integration of an AI model across the platform – search functions, project summaries, research insights, and more.

Co-designing sessions with practitioners held great value. Through card-sorting and prototype usability tests, we refined the outcome and gracely pivoted when need, stretching out the tool's capabilities.

Sift started taking shape.

All-new Research

We designed an easier and faster way to go through research papers, case studies, and
other publications.

📑

Personal Drive

Save your most valued resources, and come back at will. Just like real folders, apply tags to categorize saved files – and find them quickly.

🗂️

Team Workspaces

Team work(spaces) makes the dream work. Build projects as a team, share resources, and keep members up to speed with updates.

👩‍💻

Annotations

Call out and highlight fleeting thoughts. We created an intuitive way to add annotations to insights, summaries, and links.

🖋️

Diving into the UX

Deep Search & Smart Insights

Tool-wide integration of AI meant identifying optimum checkpoints where AI would improve practitioner workflows. I focused on designing:

1. Deep Search – find relevant resources faster.
2. Smart Insights – leverage AI to summarize or pull insights from resources.

Initial wireframe

Feedback

Finding resources specific to project location was paramount for practitioners, and simply typing in the search location would hinder specificity of location.

↓

Updated iteration

Feedback

We sliced the search bar into input field and location picker and integrated a CTA for insight generation right up front. But we faced one problem – it didn't look as important as it was.
‍
↓

Search + Insights | Home version

Impressions

Splitting Deep Search and Smart Insights was a bold step – and one in the right direction. This dual-action approach helped us assign enough importance and discoverability to both features. We further modified the UI.

↓

Search + Insights | Modified

In action

Generative insights

Insight cards make it easer for practitioners to know if they're looking at the right resource for projects. Here are some explorations.

Throughout testing, Insights cards received thumbs up. However, visual distinction remained a head scratcher. To combat this, I proposed custom fill & accent colors for AI features.

Smart Insights UI

Visual Design

Moodboard

Detailed solutions

Practitioners' Workspaces

Just like real folders, apply tags to categorize saved files – and find them quickly. The workspace enables collaboration with a Personal Archive for organizing resources and Collections for teams to share and communicate through notes. Save your most valued resources, and come back at will.

All-new Research

We designed an easier and faster way to go through research papers, case studies, and other publications.
With a standardized format, practitioners now view the most relevant content first.

Building for flexibiiy & scale

I ensured the we continually contributed to and made use of a custom design system. Sift evolved fast & often, and it was crucial to make sure changes were consistent, on-brand and scalable for extended use cases and features for the future.

Impact Measurement

The tool is currently in development with the dataset still in training.
Here are some of the anticipated impacts.

User Engagement
‍

Total user base
Rate of new users logging in
Geographic Distribution

Number of
partnered labs

Quantifying the network, and
building new collaboration ways.

Content Utilization
‍

Number of resources saved
Number of projects

Learnings

When in doubt, test it out! 🔬

A tool like this has never existed, and so we had no historic data or information to play with. Hence, we turned to user tested to validate and bust our ideas. Testing made me understand the importance of placing the user at the epicenter – building a product with stakeholders yields impactful results.

Iterate often 🌀

If the first version and the final version of Sift met, they wouldn't recogize each other. Iterations, in the right direction and with the right feedback, did make our product simpler, effective and more capable than our original brief.

Teamwork = Dreamwork

Working with this super talented team has been one of the greatest learning experiences during my time in Design. Our meetings were full of "here's an idea", honest critique, gallons of coffee, and a whole lotta laughter! From L-R: Rishma Bora, Anusha Thalnerkar, Kirtana Kannan & Myself.