Head of Process Intelligence (UK) at Capgemini Invent.

I work at the intersection of process, data, and AI system design — helping organisations turn raw operational data into something both humans and machines can reason about.

My background is in process mining and event-log engineering, but my broader interest is architectural:
how you design operational systems that are explainable, auditable, and AI-ready, without relying on fragile, vendor-specific abstractions.

This GitHub is where I explore those ideas through small, practical projects: worked examples, minimal pipelines, and early architectural experiments.

• Open-source end-to-end process mining pipelines
  Minimal implementations showing how raw operational data becomes event logs and models — outside of any specific vendor tool.

• NFL process mining examples
  A concrete, end-to-end worked example that treats an event log as a designed dataset, using public sports data to make process concepts tangible.

• Synthetic event-log generation
  Tools for creating realistic process behaviour to support demos, training, and early-stage solution design.

• Process Intelligence data assessment tools
  Lightweight scripts that explore how teams assess data quality and structure before analytics or automation begins.

• Process semantic layer (PoC)
  An experiment exploring whether lightweight business concepts can make retrieval-based AI systems more explainable and auditable — without heavyweight semantic modelling.

Across these projects, I’m increasingly focused on how explicit business concepts and rules can act as a shared layer between:

• operational data,
• human decision-making,
• and AI agents.

In particular, I’m interested in whether this layer can be made easy enough to work with that it becomes practical for real organisations — not just technically elegant.

If you’re interested in AI system design grounded in real operational work, or how process thinking translates into the AI era, feel free to explore or connect.