Evidence

Systems, cases and write-ups with verifiable proof of how I work: measured, not promised.

• Doc Live

  Architecture decisions and governance of a regulated AI agent

  A curated index into the agent's public documentation: architecture decision records, governance and diagrams, open and in three languages. It points to the sources rather than re-hosting them.

  • Agents
  • Guardrails
  • Observability
• 
  System Harness-certified

  AI agent for regulated industries

  A conversational AI agent for regulated industries, evaluated with an eight-scorer adversarial harness and key-gated guardrails. Public technical documentation; live system on request.

  • Agents
  • Evals
  • Guardrails

Let's talk