FXpress · AI Co-Pilot for Cross-Border Remittance · Interview Debrief & Synthesis

How to Read This Document

This debrief moves through three layers:

1. Cross-participant patterns — what was true across all four interviews regardless of persona
2. Where participants diverged — the spectrum from Perry to Sadie that defines the product's range of users
3. Design implications — what the interviews tell us the product must do, can do, and must not do

Layer 1 — Cross-Participant Patterns

Pattern 1 · FX Timing Is a Universal Pain Point

Every participant cited frustration with exchange rate timing — but in different forms. Jenni doesn't know what a good rate looks like. Perry doesn't have time to track it. Kang Googles it manually and has calculated exactly how much he loses by sending on the wrong day. Sadie monitors it actively but still misses the optimal moment.

The pain is not lack of access to rate information — it is the cognitive burden of having to act on it correctly, at the right time, while managing other priorities.

▸ "I don't have time to track that constantly." — Jenni

▸ "I usually end up Googling the exchange rate and trying to catch it on a 'good day' — which is kind of ridiculous." — Kang

▸ "I can't always tell if it's worth waiting." — Sadie

Design implication: FX timing assistance is not a nice-to-have — it is the primary value proposition. The AI layer must solve this problem first.

Pattern 2 · All Four Will Accept Crypto Rails — If Invisible