51 skills · 5 live boards · 4 departments
UK Mortgage Broker: AI Adoption Across Four Teams
A UK high-net-worth mortgage broker now runs 51 departmental skills and five live boards inside Claude. Finance, compliance, marketing and broker teams do their own work with AI, with human sign-off at every step.
- Commission run
- Management pack
- File audit
- Marketing check
- Content engine
- Page optimiser
- Sales board
- New business
The problem
The broker’s teams handled high-volume, knowledge-heavy work across finance, compliance, marketing and brokerage. AI demos existed, but nothing was embedded in daily work, and a generic chat assistant did not know the firm’s data, templates or compliance route.
What we built
A Claude team-account layer: a router that loads the right department skill, 51 skills across finance, compliance, marketing and brokerage, five live boards built from the firm’s own connectors, a shared memory layer, and weekly routines. Every output is a draft for human review, and client-facing work follows the FCA compliance route.
Before
- AI demos, not daily use
- Generic chat did not know the firm’s data
- Compliance work needs a human route
How it works
Route before answering. One entry point loads the department skill, so a finance question never lands in a marketing template.
51 departmental skills. Finance, compliance, marketing and brokerage each keep their own procedures, sources and guardrails.
Five live boards. Sales, new business, marketing, KPIs and content priorities read the firm’s own connectors, with no retyped figures.
A shared memory layer. Runs read and write the same state, so a routine picks up where the last one stopped.
Weekly routines. Scheduled runs prepare the Monday meetings; the team reviews the output, not the raw data.
Human sign-off. Every output is a draft. Client-facing work stays on the compliance route; nothing is sent without a person.
After
51 skills · 5 live boards · 4 departments
Stack
AI AdoptionClaudeSkillsWorkflow AutomationDashboardsFinancial ServicesUKWhy it holds up
Adoption is the product. The team runs the skills in its own sessions and the boards in its own meetings; the system does not live in a demo account. Named owners sign off each department’s output, and client-facing work stays on the FCA compliance route.
Team adoption
- Who uses it now
- Finance, compliance, marketing and broker teams. Each department has a named owner who signs off its output.
- What we handed over
- 51 departmental skills, five live boards, the shared memory layer and the weekly routines, on the firm’s own Claude team account.
- What changed
- From ad-hoc AI demos to skills the team runs in its own sessions and boards reviewed in its weekly meetings.
Related service: AI adoption, delivered by embedded engineers
More case studies
Big 4 client · fully on-premise
Enterprise RAG Chatbot for a Big 4 Accounting Firm
Multimodal retrieval over a Big 4 firm’s full compliance library, tuned for citation instead of summary — every answer arrives with its source paragraph attached.
- Juniors reading thousands of pages per question
- Seniors acting as search engines
200k calls/month · 67% booking rate vs 77% human
24/7 AI Agent Call Center: 200k Calls a Month Across 60 US HVAC Brands
Voice agents orchestrating 200,000 calls a month across 60 US HVAC brands for a 5,000-person enterprise, booking 67% of calls against 77% for human agents — within 10 points of a trained team, around the clock. Built as a product, an AI front desk that answers, books and routes, not a pilot.
- Night and weekend calls unanswered
- Staffing every shift hard to justify
US$1M collected in the first 3 months
AI Payment Collection and Reminders
The companion product to the AI front desk: it chases unpaid invoices with polite, timed reminders and a payment link, and stops the moment the customer pays or replies. It collected over US$1 million for the client in its first three months.
- Chasing payment is awkward and late
- Billable time lost to collections
First-Sprint Data Scientist
A vetted engineer embedded in your team, a shipped deliverable by end of sprint 1.
Pick a time below and you will speak with me directly. Bring the use case, the data and the constraints, and I will give you a straight view on feasibility, effort and the first thing to ship.
Book a callCat Yung
Hong Kong & London time zones

Book a call · 30 min with Cat Yung