Projects

Applied AI engineering

The useful question is not whether a demo looks intelligent. It is what the system can do, what it is allowed to change and how failure is handled.

Public personal engineering

SEG

Agent evaluation and orchestration

A Python evaluation runtime for Agent Skills. A dependency graph schedules evaluators, joins their evidence and gates whether to accept, revise or escalate.

  • Python
  • DAG scheduling
  • Evaluation
  • Staged repair
Read the engineering notes for SEG

Working prototype

EvidenceGate

Controls around model output

A Python CLI for policy retrieval, deterministic checks and optional model analysis. Unsupported citations fail closed; approval stays with a human.

  • Python
  • OpenAI Responses API
  • Citation validation
  • Human approval
Read the engineering notes for EvidenceGate

Internal product

Seller RAG

Product knowledge with a deliberate access boundary

Python retrieval from a real Seller account and a separate Semantic Kernel RAG application, using vector embeddings in Cosmos DB. Material changes stayed manual.

  • Python
  • C#/.NET
  • Semantic Kernel
  • Cosmos DB
Read the engineering notes for Seller RAG

Research and experiments

Independent explorations, with the implementation stage made explicit.

Working reference implementation

Intention Engine and OpenClaw

Practitioner work on operator controls, execution boundaries and recovery. OpenClaw provides the supporting runtime.

Discuss the implementation

Independent research and prototypes

Financial agent systems

Exploration of financial agents, simulation and reproducible experiments. These are research prototypes, not a live fund or a claim of achieved returns or academic affiliation.

Discuss the research