Engineering 19 March 2026 10 min read
Why 99% accuracy isn't enough when the output is your tax return
Building SpeaktoFinance taught us the brutal economics of the last 1%. Here's how we closed the gap.
Building SpeaktoFinance taught us the brutal economics of the last 1%. Here's how we closed the gap.
This post is a placeholder while we get the editorial pipeline online. The shape and rhythm of the page is right; the words are coming. In the meantime, here's a sketch of what this piece will cover.
Building SpeaktoFinance taught us the brutal economics of the last 1%. Here's how we closed the gap. The full piece will walk through the specific decisions, the trade-offs we considered, the ones we got wrong, and what we'd do differently with the benefit of three months on the other side.
Field notes from production builds. No abstractions, no recycled threads. If we ship something we'll write about why it worked, why it broke, and what we'd test if we were starting fresh tomorrow.
Subscribe to the dispatch below if you want the full post when it lands. One email a month, no recaps, no churn.
Notes, Finance, Clients. Same engine, three audiences. The bets that paid off and the assumptions we had to throw out.
Voice-first interfaces invert almost every UX assumption you brought from the screen. A practical playbook from production.
Websites, SEO, marketing, finance, CRM, note-taker, under one roof. The case for fewer vendors and more compounding.