United Nations: Social Protection Knowledge, Powered by LLM
The Knowledge-sharing Platform on Social Protection
The United Nations Research Institute for Social Development (UNRISD) is an autonomous research institute within the United Nations that is responsible for research and policy analysis on social development issues. One of its initiatives is the socialprotection.org platform, which aims to foster global knowledge sharing on social protection policies for academics, policymakers, and students. It enables the UNRISD to promote inclusive growth and sustainable development in low and middle-income countries.
Challenge
The UNRISD team approached Vinta intending to understand the necessary steps to launch an innovative AI-driven platform, enhancing their vast repository of over 15,000 resources on social protection. They provided a comprehensive requirements document outlining several ideas for integrating AI into their platform. They knew they wanted to leverage the advanced capabilities of AI, particularly through the use of large language models (LLMs), to enrich their database content, simplify contributions, and empower the user to find current, relevant, and trustworthy content. What they needed was the most efficient approach to achieve these goals.
Quickly recognizing their needs, Vinta's team identified the Product Discovery service as the ideal match. Through it, we materialized their vision in designing a scalable, validated, and user-friendly platform that leverages artificial intelligence to dynamically expand and improve information accessibility—ultimately increasing the chances of success by reducing development risks and investment costs.
The Product Discovery Journey
Vinta assembled a team consisting of a Product Manager, a Principal Product Designer, and a Lead Developer who collaborated with a project leader from the UNRISD team who assumed the Product Owner position. Together, we prototyped a cost-effective and polished solution in just 2 weeks.
Our Product Discovery, carefully crafted with our proprietary product discovery methodologies, immersed the team in remote workshops. Being mindful of the client's availability, we strategically minimized meetings while maintaining alignment. By the end of the journey, we aligned the scope, narrowed down priorities, and minimized development risks, ensuring optimal budget effectiveness.
Empowering the Platform with AI Capabilities
Understanding the Academic Researcher
In the early stages of the sprint, our Principal Designer identified the platform's target users as academic researchers. Based on previous research and conversations with UN stakeholders, we gained further insights into their domain, interests, goals, daily challenges, and level of technical fluency.
We then mapped all the key steps, touchpoints, and goals of the user journey through an online workshop session with the Product Owner and Lead Engineer, providing valuable input to prioritize features for the roadmap and prototype built later on.
Prototyping an AI-Powered Solution
By running diligently selected design workshops and desk research, we prototyped a solution highlighting how the platform positioned and positively differentiated socialprotection.org from other high-profile academic research platforms. The chosen solution was continuously scrutinized throughout the sprint through daily async feedback from Microsoft Teams, their primary communication channel.
We made the sign-up process significantly more efficient by highlighting all the benefits, making it stress-free to create an active profile on their platform.
Our strategic additions, which ended in the final mockups, included advanced filtering options, AI-powered features, and an enriched content repository. The AI capabilities featured a summarization tool that facilitates scanning through search results across a wide range of resources—publications, reports, case studies, academic papers, data, and research tools—keeping stakeholders informed of the latest trends and advancements in the field.
We also proposed how AI-powered suggestions could enhance the experience through contextual reading lists, personalized recommendations, and automated categorization upon content submission. These features will significantly streamline content search and contribution, transforming an arduous manual task into a simple button click, thus increasing adoption and usage.
Boosting the data knowledge with RAG
Our solution also included a Technical Assessment report outlining an architecture based on a Retrieval-Augmented Generation (RAG) pipeline. Before Large Language Models were widely available, integrating AI into a product involved months of engineering work to collect data, build training and validation datasets, select models, and fine-tune them to achieve the desired results.
The final model or even models would later be integrated with the final product. From our experience, building and training custom models is a long and error-prone task which can often be expensive for most clients.
LLM offers a significant advantage for natural language-based products. With zero-shot learning, we can handle multiple tasks that traditionally require different models and extensive training, simplifying the product infrastructure. We proposed supercharging LLM's generative ability with our client's proprietary data to get contextual results with minimal engineering effort and low cost by leveraging RAG Pipelines.
Established technologies such as vector databases and embedding techniques are added to the pipeline to augment the model's knowledge base and produce custom responses without manual training. These advancements reduce development costs and time-to-market while enhancing user experience with more natural and contextually aware interactions.
Outcome
By the end of our engagement, we effectively transformed the original requirements document, which covered many functionalities on a higher level, into a narrower, strategically focused scope with actionable outputs and estimates of the development timeline. Our delivery has significantly empowered the socialprotection.org platform by enhancing its functionalities and focus on value.
By examining the user experience within the socialprotection.org platform, we could empathize with our target persona and craft a solution that leveraged AI to impact their workflow, considering their most significant pain points and jobs to be done.
We brought in Taxonomic Tagging powered by AI, a giant time saver for submitting new resources to their knowledge base. It makes search and categorization much more powerful.
As consultants, considering the cost and time they want to invest, we recommend the best tool to solve our clients' problems. In this case, we did not choose LLMs as the solution because AI is a hot topic but because they were the best tool for the job. LLMs have enabled applications that would be very costly to implement, so we are attentive to cases where we can use LLMs effectively in instances where they solve problems that traditional solutions would not be as efficient at solving.
These improvements will facilitate more effective research and collaboration within the community and ensure the platform remains a vital resource in social protection.
What does the client think of Vinta?
On behalf of the SP.org team, I deeply thank Vinta's team for their kindness, professionalism, and extremely high-quality work. The deliverables will be highly useful in building the platform.
- ICT Associate