Daily Briefings
Rather than layering more relevance signals on the original feed, I designed Daily Briefings as a separate personalized morning view. The Feed stayed the firehose; Briefings became the context-setting starting point.
Shaping AI
Product Vision.
Creating the workflows of the future with an evolving AI product — turning unmet needs into a coherent product vision at speed.
- Challenge
- Redesign how a voting rights research team captured, curated, and trusted what the AI scaled system produces.
- My Role
- Lead product and service designer. I owned discovery, the product audit, the sprint roadmap, and the new designs — from framing the problem through prototype and built solution.
- Team Structure
- Lead Designer (me), 2 Engineers, 2 Product Managers, Client, Creative Director took over as I transitioned off the project.
- Impact
- Increased workload visibility and accelerated monitoring and search workflows.
Overview
I joined a team that had done discovery by the book: requirements co-created with users and a roadmap full of requested features. The product still was not working for them. I shifted the work from feature delivery to creating the workflows of the future with an evolving AI product — uncovering unspoken needs, making a coherent vision tangible quickly, and moving from mapping to tested designs without losing delivery speed. The result connected prioritization, research, trust, and team visibility into one workflow.
The problem.
The first view isolated the repeated search pattern: broad and specific queries both led to the same scan-and-flag loop.
The full map revealed the wider problem. The product supported moments of the work, but not the connected daily workflow around prioritizing, monitoring, reviewing, and sharing research.
This was not a technology problem. It was a people and workflow problem.
Discovery.
Twenty-eight interviews across leadership, management, and research assistants revealed the unspoken needs the original requirements had missed.
New Product Vision.
I turned the research into a coherent system for creating the team's future workflow quickly — not another disconnected list of AI features.
A shared primitive.
The new vision started from one reusable summary that connects many inputs to analysis and the next action.
The product vision.
Built out from that primitive, the product came together as news, search, collections, coverage, and profiles.
Sketching the product.
Fast, low-fidelity sketches made the future workflow tangible enough to test, challenge, and evolve with the team before slowing down for polish.
The morning brief.
The day now opens with a prioritized brief — the updates that matter, counted and ready to scan, instead of an inbox of raw feeds.
Before In between and after.
Before.
An untriaged feed.
The feed collected information without helping researchers decide what needed attention first.
In between.
A focused morning brief.
The day opens with a Morning Brief — a rapid signal about what deserves attention first — with Top Stories as its scannable citation.
TrustTransparencyDynamic
After.
Key design moments.
Team Coverage
A strip showing each researcher, their new item count, and reviewed fraction created a shortcut into focus-area filters while giving managers a clearer view of capacity.
Source Coverage
An internal dashboard made ingestion success visible through a summary strip and per-state status cards. Researchers could expand a jurisdiction, inspect its scraped sources, and preview content without losing context.
Kev AI Search
I turned Explore from a blank search bar into a dual-mode surface — keywords for broad clip search, or a question for a synthesized answer with source clips attached. Suggested prompts reduced the cold-start problem for new users.
Outcomes.
A broader product direction emerged from looking past the feature list and into the rhythms of the work itself.
28
User interviews across leadership, managers, and researchers
11
Law-firm researchers using the redesigned workflow
3 tabs
Restructured into briefings, search, and coverage
