Skip to content

Projects

Selected work

Each entry records the problem, the decisions that mattered, and the measurable outcome. Filter by discipline below.

AI Training2026

AI agents that answer customer reviews

Led end-to-end development of review-response agents on OpenAI and Claude, with tool integrations and memory for autonomous operation — and a prompt framework that cut model cost 18%.

  • 18% reduction in model cost with no loss of response quality
  • Tool integrations and memory for autonomous, multi-step operation
PythonNode.jsOpenAIClaude
Backend2025

Holding 99.9% sync uptime across three review platforms

Resilient integrations with Google Business Profile, Yelp and Facebook Reviews — webhook-driven where the platform allows it, scheduled where it doesn't, reconciled either way.

  • 99.9% data-sync uptime across three third-party platforms
  • Webhook and scheduled paths reconciled against one another
PythonNode.jsRESTGraphQL
Frontend2022

Dashboards that made AI output reviewable

React and Next.js dashboards surfacing AI metrics and generated responses for client decision-making — increasing engagement 28% by making the model's work inspectable rather than opaque.

  • 28% increase in client engagement with the platform
  • AI-generated responses reviewable and editable before publishing
ReactNext.jsTypeScriptData visualisation
Backend2023

Cutting release cycles 40% with containerised delivery

Dockerised CI/CD onto Kubernetes for cloud-native Python and Node services, plus a data-model redesign that doubled pipeline throughput for AI processing.

  • 40% faster release cycles
  • 2× data throughput after the pipeline and schema redesign
PythonNode.jsDockerKubernetes