[ Case study ]
Factiva AI Assistant
Building a trust-first AI research experience: a conversational assistant shipped inside Factiva, grounded in Dow Jones licensed content and traceable to checkable sources.
- Client
- Dow Jones - Factiva
- Role
- UX Architect
- Year
- 2026
- Disciplines
- AI / UX, Design Systems
Shipped
Live in Factiva for Dow Jones subscribers
Cited
Every significant claim links to a checkable source
Licensed
Grounded in Dow Jones content, not the open web
[ Information architecture ]
Chat
- Prompt
- Responses
Sources
- Citations
- Documents
History
- Saved
- Recent
Confidentiality notice
This work spans active platform strategy, shared AI capabilities, and multiple product surfaces. To respect that, this case study stays intentionally high-level, focusing on the cross-brand design problem, platform principles, and reusable outcomes rather than brand-specific implementation details.
Dow Jones shipped the Factiva AI Assistant, a conversational research assistant inside Factiva, the platform professional researchers, analysts, and journalists rely on. I led the UX architecture: the conversational interaction model and, at its core, the trust and citation pattern language that lets a professional stand behind every answer it gives.
The challenge
For Factiva's users the bar was never speed, it was credibility. A faster answer about a company or an industry is worthless if it cannot survive legal and editorial scrutiny, or be put in front of a client. The assistant had to differentiate from commodity chatbots not through raw capability but through verifiability, every answer something a professional could defend.
- Ground every answer in Dow Jones licensed content, never the open web
- Make each significant claim traceable to a checkable source
- Be honest about uncertainty, including when trusted sources disagree
[ Protected layer ]
The full case study is available on request.
High-fidelity screens, information architecture and the detailed process for this enterprise project are shared under NDA. Enter the access password, or request access and I will share the full walkthrough.