← All case studies

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.

broker-skills.board51 skills · 5 boards
Finance
  • Commission run
  • Management pack
Compliance
  • File audit
  • Marketing check
Marketing
  • Content engine
  • Page optimiser
Brokers
  • Sales board
  • New business
Illustration

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. After: 51 skills · 5 live boards · 4 departments.

Before

  • AI demos, not daily use
  • Generic chat did not know the firm’s data
  • Compliance work needs a human route

How it works

  1. Route before answering. One entry point loads the department skill, so a finance question never lands in a marketing template.

  2. 51 departmental skills. Finance, compliance, marketing and brokerage each keep their own procedures, sources and guardrails.

  3. Five live boards. Sales, new business, marketing, KPIs and content priorities read the firm’s own connectors, with no retyped figures.

  4. A shared memory layer. Runs read and write the same state, so a routine picks up where the last one stopped.

  5. Weekly routines. Scheduled runs prepare the Monday meetings; the team reviews the output, not the raw data.

  6. 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 ServicesUK

Why 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

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 call

Cat Yung

Hong Kong & London time zones

Book a call · 30 min with Cat Yung