What I Build

Reliable Python systems, tooling & scientific software

Focused engineering services built around one idea: systems that are predictable, observable, and hard to misconfigure. Whether you need a one-off tool, an integration, or ongoing support, here's what you can work with me on.

< Services />

Every engagement is scoped to a concrete outcome — not billed hours against a vague brief.

🧩 Configuration & Validation

Schema-driven validation layers (JSON Schema, YAML, typing.Annotated) that reject invalid configuration before it ever runs.

→ Fewer silent failures & misconfigurations
Discuss this →

🤖 AI Workflow Reliability

Deterministic, observable LLM pipelines using the LLM Workflow Router — topology validated before execution, with tracing built in.

→ AI workflows that don't silently break
See the product ↓

🛠️ Developer Tooling & CLIs

Internal tools, command-line utilities, and developer-experience improvements that reduce friction and make systems easier to operate.

→ Faster, calmer engineering workflows
Discuss this →

🔬 Scientific Software

Python tooling, configuration systems, and simulation support — the kind of work shipped in the official ESA Pyxel 2.14 release.

→ Reproducible, trustworthy pipelines
Discuss this →

📐 Architecture Review

A focused read of your system's trust boundaries, data flow, and failure modes — with clear, prioritized recommendations you can act on.

→ Risks made visible before they bite
Discuss this →

📝 Technical Documentation

Developer-facing docs, architecture write-ups, and case studies written by someone who reads the code — clear writing as part of the build.

→ Docs people actually use
Discuss this →

< LLM Workflow Router />

Reliable Infrastructure for AI Workflows

The LLM Workflow Router helps engineering teams build AI applications that are predictable, observable, and easier to operate in production. It validates workflow topology before execution, eliminates invalid routing paths, exposes explicit failure states, and integrates with OpenTelemetry for end-to-end visibility—reducing the risk of unexpected behaviour in complex AI systems.

Inspired by the Lumenoid AI Framework, the router focuses on structural safety rather than content moderation. Lumenoid helps applications make responsible AI decisions, while the LLM Workflow Router ensures those decisions flow through explicit, deterministic, and auditable workflows.

Free MIT-licensed Core • Optional Commercial Security Licensing

pip install llm-workflow-router

Start with the free MIT-licensed core. Upgrade to the Commercial Security Layer when you need trust-boundary enforcement, policy validation, tamper-evident auditing, and enterprise support.

Deterministic workflow execution
YAML-driven workflow configuration
Multiple explicit entrypoints
Strict topology validation before execution
Cycle detection and safe re-entry handling
Clear failure states and predictable behaviour
Optional stateful session layer
OpenAI Agents SDK integration
Mermaid / DOT topology export
OpenTelemetry observability
CLI tooling for validation and analysis

🛰️ Inspired by the Lumenoid AI Framework

Lumenoid is an open ethical AI architecture that defines reference principles for responsibility, transparency, uncertainty, bounded capability, and human-centred system design. Rather than prescribing model behaviour, it provides architectural foundations that help AI systems remain understandable, accountable, and safe to evolve.

🛡️ Licensing

The core LLM Workflow Router is free forever under the MIT License, including commercial use.

Organizations that need enterprise-grade trust boundaries, policy enforcement, tamper-evident audit trails, and the wfrouter.security.* telemetry convention can license the optional Security Layer.

Commercial subscriptions include ongoing security updates, evolving policy packs, compatibility with OpenTelemetry GenAI conventions, and priority support.

💼 Commercial Security Licensing

Tier Annual Price Designed For
Indie£290Individuals
Team£1,200Growing teams
EnterpriseFrom £4,500Large organisations
✔ Trust boundary enforcement
✔ Policy validation
✔ Audit trail
✔ Security telemetry
✔ Priority support
✔ Commercial license

< Install & Use My Open Tools />

Most of what I build is free and open. Install it, use it in your own work, or support it if it helps you.

< Have a system that needs to be reliable? />

Tell me what you're building or where things keep breaking. I usually reply within 3–5 business days.

💻 Start a conversation →