Work

Systems that had to work on Monday morning.

Fourteen years of engineering, described as engineering. Client, employer and product names are withheld — most of this work sits under confidentiality agreements — so each case study describes the problem, the architecture and the decisions instead. Figures are only the ones I can stand behind.

AI & retrieval

A knowledge assistant that answers from your own documents

Documents turned into something people can simply ask — hybrid search rather than vector similarity alone, a reranker that cuts forty candidates to six, and a numbered citation on every answer pointing at the document and page it came from.

RAGHybrid retrievalRerankingpgvectorPostgresFastAPICeleryRedisObject storageDocker

AI agents & real-time

A voice agent that takes the call, looks it up, and answers

A caller rings, speaks normally, and gets an answer drawn from live business data — transcription running while they are still talking, a model working out what they actually want, and a query against the systems that already hold the answer.

Telephony integrationStreaming speech-to-textLLM intentSystem APIsRedis queuesReal-time audio

Automation & generative AI

An unattended production pipeline: a topic goes in, a finished video comes out

A pipeline that takes a topic, researches and scripts it, generates the narration and the visuals, renders the video and files the result — with no human step in the middle. Built partly as a product and partly to learn where multi-stage generative systems fail in practice.

n8nLLM orchestrationStructured outputText-to-speechImage generationVideo renderingCloud storageQueues

Automation & integration

Taking pressure off a contact centre by moving routine requests out of the phone queue

A messaging channel and a set of automated self-service flows added to an operation where call volume was rising faster than headcount — so routine requests stopped needing a person, and the calls that did land got answered sooner.

Messaging platform APIWorkflow automationSelf-service flowsCRM integrationBackend services

Real-time systems

Live telemetry for a commercial vehicle fleet

Continuous data from vehicle-mounted devices turned into live maps, geofence alerts, fuel and maintenance tracking and operational reporting — across a web portal and native apps on both platforms, architected to keep working as the fleet grew.

IoT ingestReal-time processingGeofencingMappingPush notificationsNative Android & iOS.NETSQL ServerPublic APIs

Systems & integration

Turning a national cultural institution into a connected digital exhibition

Six interactive visitor applications running across more than a hundred devices — touch tables, kiosks and screens — all fed and updated from one central content system, so curators could change an exhibit without anyone touching a device.

AndroidPHPPythonCentral CMSContent synchronisation3D modelsTouch tables & kiosks

Process automation

Clinic operations, from reception to dispensary, on one system

A paper-based clinic workflow replaced by a connected system covering the whole patient journey — reception, screening, consultation, laboratory and dispensary — with medical protocols and prescribing rules managed centrally and rolled out to every site.

AndroidPHPClient-serverCentralised protocolsRole-based modules

Process automation

Replacing paper field surveys with dynamic forms and a live operations view

Field teams moved off paper and onto tablets, with survey forms and their validation rules defined centrally rather than built into the app — so a new survey type became a configuration change instead of a release.

AndroidPHPDynamic formsValidation engineOffline captureTask allocationReporting

Mobile & scale

A nationwide education platform built for places with almost no connectivity

A mobile application for tracking classroom engagement and application use across a school network of more than a thousand sites — engineered to work properly in remote areas where connectivity is intermittent at best.

AndroidOffline-first architectureSync & conflict resolutionUsage analyticsBackend services

The offer

A free AI & automation opportunity review.

You do not need another generic AI strategy document. I look at how your business currently works and come back with practical opportunities where AI, automation, integration or better architecture would reduce manual work and create measurable value — including the ones I would tell you not to bother with.

Two minutes to request. The written map is yours whether or not you hire me, and there is no follow-up sequence.

  • 01UnderstandYour current workflow, tools, systems and where things get stuck.
  • 02IdentifyRepetitive work, manual handoffs, disconnected systems, AI-shaped problems.
  • 03PrioritiseSeparating interesting ideas from the things that would move the business.
  • 04RecommendPractical opportunities ranked by impact, complexity and likely return.
  • 05ImplementIf you want it built, I design and build it. If not, the map is still yours.