Product Design
Information Architect
Prototyping
User Testing
Designing an AI-powered assistant for hedge fund analysts to automate earnings call prep, extract KPI insights, and generate context-aware follow-up questions — all while preserving trust and control.
I worked with a fund founder and an AI engineer to build a 0→1 internal tool that reduced analyst prep time by over 80% and introduced a repeatable, transparent research workflow.
Analysts spend hours parsing transcripts, building KPI models, and writing prep docs. The process is fragmented across tools and wastes valuable time.
💡Opportunity
Streamline the research workflow by automating repetitive tasks — without breaking existing habits.
Most AI tools offer shallow summaries with no structure, traceability, or real insight. Analysts can’t trust what they can’t verify, so they don’t use it.
💡Opportunity
Design an AI assistant that speaks the analyst’s language, shows its sources, and earns trust through control.
A modular web tool where hedge fund analysts can upload earnings calls, instantly extract KPIs, surface key quotes, and generate custom follow-up questions — all with traceable sources and editable outputs. The system fits directly into existing workflows, reducing prep time from hours to minutes and standardizing analysis across teams.
AI-generated follow-up questions based on KPI movement, soft guidance, or missing context. Each question is editable and backed by the exact quote or metric that triggered it.
✅ Win: Analysts adopted 80% of AI-generated questions into live meetings — cutting prep time while maintaining precision.
The tool produces concise summaries of earnings and corporate access calls, segmented by topic and supported with direct citations. Every insight links back to a quote or metric — so nothing is taken at face value.
✅ Win: Analysts skipped 60+ page transcripts and trusted the assistant as a starting point for post-call debriefs.
Extracted financials auto-populate a table that shows quarter-over-quarter changes with visual highlights. Analysts can edit values and trace them back to original statements instantly.
✅ Win: Updating models took minutes instead of hours — with full control, context, and exportability.
We started with a paginated, step-by-step experience — transcript → KPIs → quotes → questions. It followed conventional UX thinking, but broke down in practice. Analysts don't work linearly; they cross-reference constantly, spot anomalies mid-scroll, and toggle between insights without following a script.
We shifted to a single-page interface with collapsible sections and inline editing. This let analysts jump between quotes, metrics, and questions without losing momentum — mirroring their real-world, non-linear workflow.
Win: Trust and adoption improved immediately. Analysts could now stay in flow and work the way they think — fast, messy, and insight-first.
