Lead Product Designer & Builder · Financial Finesse · 2026
I designed and built an AI content studio that localized our content for 25 countries at one country a day — work that would have cost $2.44M and taken 9 months by hand.
Financial Finesse's people were quietly using their own unregulated AI subscriptions to write company content. I built one tool, trained on our voice and compliance rules, that replaced all of it — then turned it into a localization engine that adapts content for any country in the world. Solo, zero to one, with Claude Code.
Financial Finesse's team was writing company content on scattered, unregulated AI subscriptions. I designed and built Global Content Studio — one brand-trained AI studio with an 8-step localization pipeline (Atlas) — solo, with Claude Code. It localized ~650 pieces into 25 countries in 25 days: work that would have cost $2.44M and taken 9 months by hand.
- Role
- Lead Product Designer & Builder
- Timeline
- 2026 · ~2 wks to build, 4 to refine
- Team
- Solo — with Claude Code
- Scope
- Strategy · UX/UI · AI training · Build
Strategy, design, AI training, and the build — end to end
Spotted the risk in the team's scattered, unregulated AI and defined the product — then saw where the company was headed and pivoted it from a writing tool into a localization engine.
UX, UI, and the authoring workflow — from a single prompt to a compliance-checked, localized asset, one country at a time or in bulk.
Built the brand voice, compliance rules, and the per-country LLM Wiki the model runs on — the source-of-truth layer that makes generic AI safe for Financial Finesse.
Coded the entire app myself with Claude Code, zero to one, no engineering help — first working version in about two weeks, refined over four.
Designed the Atlas pipeline and the human-in-the-loop QA that lets it run at scale — in production, localizing our library across 25 countries.
Everyone had an AI tool. None of them sounded like us — and then we decided to go global.
Last year, AI went from novelty to daily habit across the company. Most of the team reached for it to write and edit content — each on their own paid subscription, each with no guardrails. The output was fast, but it didn't sound like Financial Finesse, and we had no way to regulate what any of it said. In a business built on financial trust, that's a real risk.
Then the company set its sights on every market. Localizing our library the traditional way would have meant hiring one in-country specialist per market, then having each of them translate, culturally adapt, and QA every single item — slow, expensive, and impossible to scale.
From a writing tool to a localization engine
I pivoted the studio from writing content to writing and localizing it. It can take an existing article or write a brand-new one, then adapt it for any country in the world — one at a time or in bulk. Not a translation. A rewrite in the correct tone, financial structure, customs, and culture.
Brand-trained AI. Grounded in Financial Finesse voice pillars, compliance rules, and content schemas, running through the Anthropic API. Every draft comes back already sounding like us — not like generic AI.
LLM Wiki — our source of truth. For each country, I built a knowledge base the model pulls from. Instead of scraping the open web for financial facts, the AI draws from vetted, country-specific sources we control. That's what makes localization accurate instead of a guess.
True localization, scored. Each output is rewritten for the correct tone, financial structure, customs, ways of life, religion, and culture — then scored at least 0.9 on each dimension. The tool explains why it changed what it changed, and flags anything it's unsure about for a human to check.
Human in the loop, always. Every article gets human QA before it ships. A coach reviews and signs off on what the system flags. The AI does the heavy lifting; a person always has the final say.
Inside Atlas — what happens to every article
Every article moves through Atlas, an 8-step pipeline — whether it's brand-new or being localized. It starts with a fit check that decides whether the piece even belongs in that market (if it's built around something that doesn't exist there, we don't localize it), then runs eight controlled steps. Confidence scoring runs across the whole pipeline: each output is rated at least 0.9 on tone, financial structure, customs, culture, and compliance.
Hover or tap a step to see what happens and why it matters.
Designed and built solo. Zero to one, no dev team.
I built this entire app myself with Claude Code — from zero to one, with no engineering help. The first working version came together in about two weeks; I spent the four after that tuning the pipeline until every step held up under real content. A traditional version would have needed a PM, a designer, and a multi-person dev pod running for months. I did it as one designer who can build — directing AI, shipping production code. Here's what the localization run would have cost the traditional way, by hand:
"A tool one designer built in two weeks changed what our company thought it could go after — and helped us win the Federal Reserve."
Impact
9 months of work, done in 25 days — in production today.
Net cost avoided vs. hiring 25 in-country localizers — 99.1% lower
Countries localized from one authoring system — 16,250 on-brand outputs
Employees reached through the content the studio produces
Global Content Studio writes in the company's voice — and takes that voice global, localizing an entire content library for 25 countries accurately, at a fraction of the time and cost. It turned a US company into a global one — in days instead of years.