Moha Intel
The first build failed in testing. The rebuild became a research workspace analysts trust.
The first version failed in testing. Users couldn't finish basic tasks. The rebuild turned an AI demo into a working research tool for analysts at three companies.
Role
Lead product designer. I owned what the product is. I owned the information architecture and the interaction patterns. I held them through every round of testing.
Team
Lead designer, researcher, frontend developer, backend developer
The challenge
AI chat resets with every session while research is continuous . Notes vanished, sources were untraceable, so analysts could never build on their own work.
The approach
Rebuild around four persistent surfaces . Show proof at every step. That means visible sources, save states, and version history.
The problem
Research is continuous; a chat window treats it as disposable.
The first build failed
Analysts could not finish basic tasks. The reason was memory.
Researchersneededmemory.
From chat to research workspace
Four persistent surfaces replaced the chat window: notes, writing, channels and sourced summaries.
Validation
Tasks that failed in round one became routine, with sources cited with confidence.
Validation results
Designing for trust
Clickable sources, save marks and version history, human input marked from AI output.
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 hard problems were words, not technology. One wrong term derailed a whole task flow.
- Insights2/3
Analysts trusted it once it showed its reasoning.
- What’s next3/3
Shared channels, live co-editing and smarter memory.
Swipe to explore