Work and case studies

Work

Most of my client work is private. These are the systems I can talk about: a live UK structured-products investment platform, seven years of technology leadership at a £1bn+ advice firm, and the products where the agentic AI patterns were worked out.

Client project · Hamilton Thomas

Autocalls — Hamilton Thomas

Designed, built and now operates a UK structured-products investment platform for retail investors and their advisers. Delivered in under a year and live on the web with its first investors.

Case study · Lowes Financial Management · 2018 to Sep 2025

Seven years running the technology of a £1bn FCA-regulated advice firm

The estate. When I took it on as Head of Software Development, the firm ran 44 applications and 45 databases, built over years in whatever was current at the time: Visual Basic, VBA, C#, Angular, and later TypeScript and React, on SQL Server and MongoDB, across multiple virtual machines, alongside third-party systems. I took charge of all of it, from the servers and databases to the code, and brought it together in stages: first into two core systems, then into one unified platform. Staff worked in one place instead of many.

Leadership and adoption. I led a technical team of five, reporting to the managing director, and owned software, infrastructure, security, backup and disaster recovery, suppliers and data. I supported more than 80 staff through the adoption of new platforms. I also served as Deputy Data Protection Officer, with GDPR Foundation / Practitioner training from IT Governance (2022).

What I built. A React investment onboarding platform rolled out to more than 80 staff including 18 advisers, which cut application processing time by over 90% and removed paper applications entirely. A direct-to-consumer digital platform. AI-driven portfolio analysis tools. Migrations to modern virtualised infrastructure.

Client reporting. Accountable for six-monthly client valuation reports and annual costs and charges reporting for over 4,000 clients, ensuring accuracy before issue.

The exit. After the firm's multi-million-pound sale, I led the Lowes post-sale integration into the acquiring group: data migrated, overlapping platforms merged, legacy systems decommissioned. I was retained afterwards as a consultant by the managing director who sold the firm.

Intelliflo OfficeReactSQL ServerData migrationIntegrationInfrastructure
>90%
reduction in application processing time, with paper applications removed entirely
44
applications and 45 databases run for 80+ staff and 5,000+ clients
5
technical team members led, reporting to the managing director
Products

Products where the patterns were worked out

I build my own products with the same tools I recommend. They are where the approval flows, MCP servers, voice agents and guardrails were first proven.

Ship Keys

Launch-readiness checks for apps built with AI coding tools, delivered as a Claude connector and a Claude Code plugin, with autonomous agents running in customers’ CI pipelines. Private beta at shipkeys.ai.

Claude connectorClaude Code pluginAgents in CI
shipkeys.ai

Mini Calls

A phone and web voice agent with multi-agent hand-off and secured actions. Built on Pipecat and Google Cloud Run, with MCP clients for tools.

Voice agentPipecatCloud RunMCP client

Mini Steps

Persistent goals and context across conversations, with owner-approved actions, per-call metering and spending limits. End-to-end voice interaction through the MCP connector. Private beta.

End-to-end voiceOwner approvalMCP connectorPrivate beta

Mini Navigator

Daily records for families of children with additional needs, summarised by AI, with strong privacy controls and model choice by query complexity. In development.

Privacy controlsModel routingIn development

Mini Ops

Weekly AI competitor reports for small businesses, with owner approval before anything is published or sent. Prototype.

Scheduled reportsOwner approvalsPrototype

Mini Engine

Review-pack drafting with RAG and LangGraph pipelines, human approval checkpoints and evals, built on synthetic data. Prototype.

RAGLangGraphApproval checkpoints
Before fintech

Earlier engineering: regulated and safety-critical

The habits came from places where software failure had physical consequences.

2005 to 2008
Steve Minnikin Financial ManagementSoftware engineer and regulated financial adviser in a family advisory firm under the FSA. Bespoke C# and SQL Server systems supporting a doubling of business.
2004 to 2005
Microsol, GatesheadSCADA and HMI systems for fault analysis in power transmission and distribution.
2002 to 2004
Rolls-Royce, Gateshead and BristolTransmission and distribution of power; aerospace asset management. Led recovery of a failing server-side application project, restoring a major client’s confidence.
2001 to 2002
Capita, Darlington and LondonSystems for Europe's largest smart-card launch; managed 12 testers and secured a £1m milestone.

Want the detail on any of these?

Ask on the first call. I am happy to walk through the architecture, the controls and what I would do differently.

steve@minibit.co.uk · Newcastle upon Tyne, working across the UK