Moha Intel
Multi-source synthesis workspace for investment analysts.
An AI research workspace for investment analysts working across documents, conversations, and live data.
Role
Lead product designer owning product definition, information architecture, and interaction patterns through iterative testing cycles.
Team
Lead designer, researcher, frontend developer, backend developer
The challenge
Existing AI chat tools treated research like a conversation, but research is continuous . Sessions reset every time, notes disappeared, and sources were completely untraceable, so analysts had no way to build on their own work.
The approach
Restructured the product around four persistent research surfaces with embedded trust signals, source attribution, save states, and version history, validated through iterative testing.
The problem
Analysts worked with fragmented tools that broke their focus on every switch, sessions offered no persistence so notes disappeared constantly, sources were completely untraceable, and broken context meant every session started from zero.
Discovery through testing failure
The first version failed immediately in testing, revealing that the core issue wasn't usability but a fundamental lack of memory that forced researchers to start fresh every session.
Researchersneededmemory.
From chat to research workspace
The core redesign replaced a single chat window with four persistent surfaces, each solving a specific failure point from testing.
Validation
Previously impossible tasks became intuitive. Users saved, built on previous work, and cited sources with confidence.
Validation results
Designing for trust
Trust wasn't about better AI. It was about visible proof at every interaction.
Trust architecture
Key risks of investing in Kumamoto?
Population decline accelerating, TSMC inflates land values
What are the key risks of investing in Kumamoto prefecture?
Three factors: population decline is accelerating faster than national average, TSMC facility construction inflates short-term land values, but infrastructure spending signals long-term regional commitment
- Challenges1/3
The hardest problems were conceptual, not technical. Wrong terminology derailed task flows, and multi-topic synthesis had no existing patterns to follow.
- Insights2/3
The solution wasn't better AI, it was better feedback. The interface had to make the system's reasoning visible.
- What’s next3/3
Evolving into a collaborative surface: shared channels, insight extraction, live co-editing, and smarter memory.
Swipe to explore