GIC

Building an AI platform for financial professionals

BACKGROUND

GIC is a sovereign wealth fund with an estimated US$800B in assets under management and 11 offices across key financial hubs. Driven by recent advances in artificial intelligence, it aims to build a new way for investment professionals to conduct research at scale and generate alpha through data.

MY ROLE

As a product designer on the AI taskforce team, I helped define the product vision and design the company's first AI platform, ChatGIC. This involves working closely with data scientists, engineers, and investment professionals to create a seamless and intuitive interface that empowers users to leverage AI in their investment research.

Prompt to begin

—

ChatGIC represents a transformative approach to investment research at GIC. The platform introduces a prompt-first interface where investment professionals begin their research journey through natural language interactions, similar to having a conversation with an expert research assistant.

I designed this unified experience to streamline complex investment workflows into an intuitive interface. The platform integrates multiple data sources and tools into one cohesive system, allowing users to initiate and conduct comprehensive research through carefully crafted prompts that guide them toward meaningful insights.

Investment professionals can leverage these specialized prompts - from market analysis to due diligence workflows - all within a single platform. This consolidation eliminates the need to navigate multiple systems, significantly reducing research time while maintaining high-quality outputs through structured, prompt-driven interactions.

Sources

Investment professionals need access to diverse data sources to make informed decisions. To ensure that the AI platform draws on accurate and audited data sources, I designed a unified data integration layer that seamlessly connects internal proprietary databases with external market feeds, alternative data sources, and third-party research platforms.

The platform intelligently combines structured financial data with unstructured content like news, research reports, and regulatory filings. This allows analysts to quickly surface relevant insights across multiple sources through natural language queries, rather than manually piecing together information from disparate systems.

Expanding to voice mode

To enhance productivity during research and analysis, we expanded ChatGIC's capabilities to include voice interactions. Investment professionals can now dictate their queries and thoughts during document review, automatically converting speech to structured prompts while maintaining context.

The voice mode integrates advanced natural language processing to accurately transcribe industry-specific terminology and financial jargon. It also provides real-time summarization of long-form content and meeting discussions, allowing analysts to focus on strategic thinking rather than note-taking. This feature has been particularly valuable during investment committee meetings and company management calls, where rapid information processing is crucial.

Library

—

To unify the needs of various departments on a single AI platform, I designed a centralized repository where users can access a curated collection of design prompts tailored to various aspects of the investment and deal workflows.

This library is a source of inspiration and guidance, offering prompts that provide a structured starting point to accelerate research tasks while maintaining consistency across teams.

Version control and tracking

—

Investment research through AI often involves an exploratory process with multiple prompts and conversation branches. We observed that analysts frequently used a trial-and-error approach, experimenting with different prompts until finding the most effective path. Users would often save promising responses manually and restart conversations to build upon successful interactions.

To streamline this workflow, we introduced version control concepts borrowed from Git such as commits and branches. Users can now save key milestones within their conversations and create multiple branches from these points. This allows them to either continue productive lines of inquiry, revert to previous states if needed, or spawn new conversations that retain the context of successful prompts.

Report drafting

—

One of the key challenges we faced is in developing modes. As the product had to serve a wide range of users across different disciplines, it was necessary to include different modes that cater to their specific needs. The most crucial mode was the Research Assistant Mode, where the vast majority of investment analysts would use to gather their investment insights and build financial models. By scoping the features within each window to the specific mode, we were able to tailor the experience to the users needs.

Result and impact

80%

Adoption across the organization

56%

Improvement in average time to prepare data visualizations

24%

Reduction in average time spent to write investment reports

ChatGIC launched in mid 2025 and quickly achieved widespread adoption across GIC's investment teams. As usage grows, the platform continues to evolve by leveraging decades of proprietary investment knowledge and expertise. This data-driven approach enables GIC to harness collective intelligence at scale, strengthening its competitive advantage in the global investment landscape.

Figures here are intentionally reported by percentage values to obscure true scale.

NEXT CASE STUDY

Endowus

Designing a recurring investment feature

Read Now