From Six Browser Tabs to One Decision
An AI layer that watches a portfolio all day, scans the market, and gives managers a conclusion they can check before they act on it.
The cognitive bottleneck
Every morning, hedge fund managers manually cross-reference six systems — news, X, forums, commentary — to understand what moved their portfolio overnight. That synthesis happens entirely in their head. As one manager put it: "that time is worth a fortune." The question: could an AI layer do that work before they even sit down — without becoming a seventh system to manage?
"The understanding happens entirely in your head — and the time it takes is worth a fortune."
(a portfolio manager, in interview)
The challenge was to integrate trust into a high-volume system
1. The volume ruled out a read-and-clear model.
~90 messages per ticker, per day — 3,000+ signals across a book. At that scale, treating signals like notifications to clear one by one wasn't sustainable.
2. Trust is non-negotiable when decisions have financial consequences.
Managers wouldn't act on a signal they couldn't trace to a source and a formula. The system had to show its reasoning, not just its conclusion. Every competitor was reactive — paste a CSV, get a summary — with no traceability and no continuity.
3. Managers already have a filtering logic.
Every interview surfaced the same behavior: managers navigate by entity first — ticker, portfolio, source.
AI surfaces signals, the manager reads them, AI helps investigate them
1. Structure: default by priority, narrow on demand
Trade-off: Severity tabs with counts ("40 Critical"), or a single feed ordered by recency and criticality? Chose: A single feed — counts invite clearing, scanning invites reading.
Trade-off: Require a filter before showing anything, or make filters optional? Chose: Optional filters — ticker, priority, source — layered on top. Ticker is used most, narrowing to whatever's moving that day.
Trade-off: Investigate on the home page, or keep it a glance? Chose: A glance, routed to a dedicated page for investigation. Why: the morning problem is fast synthesis — what changed and why. Investigation is a choice the manager makes after scanning, not the first thing they see.
2. Workflow: scan, read, and ask work as one action
Trade-off: Separate views, or all three on one screen? Chose: One screen, three escalating steps — scan, expand, ask. Why: each step costs slightly more than the last, matching how much the manager has committed to. Verification happens while reading, never on a separate page.
3. Trust: fact, AI interpretation, and checking credibility
Four UX patterns shaped the approach: source attribution; separating fact from interpretation; progressive disclosure, showing the conclusion first and evidence on request; and human oversight signals, visible cues to confirm before acting.
Shortening the distance from signal to decision
1. Structure
Clicking a signal moves from the "scan and read" state into the full investigation:
2. Workflow
Each card escalates in three taps:
Scan (zero tap). Exactly what's needed to judge relevance. (Progressive disclosure.)
Read (one tap). The chevron expands the card to reveal the full read.
Ask (one more tap). The signal stays in view while it's questioned, and switching to the next one is just as simple. At this volume, the workflow has to support moving on, not just diving in.
3. Trust
One habit confirmed. The bigger bet was only ever a demo.
The one thing confirmed by real interviews: managers navigate by ticker and portfolio first.
The rest — the whole idea of "ask, then trust the answer" — was only shown as a demo. It was never used day-to-day, so we don't actually know if it works in practice.
Accuracy alone won't break a decade-old habit
Interviews showed the AI's answers were accurate, and that the navigation matched how people already think. What they didn't show is whether being accurate is enough to get someone to change a habit they've had for years. Next time, I would:
1. Focus on one specific moment in the existing routine, instead of trying to replace all of it.
2. Aim for one clear moment where the AI catches something the manager would have missed — something they can point to.
3. Watch where people actually get stuck, instead of asking them where they think they'd get stuck.