Case studies

Projects

Four bodies of work, one thread: decompose the problem, build the system, verify the result with evidence. Each case study follows the same shape — the problem, the build, and the proof.

• Prismatic Engine

  Open-source multi-agent orchestration engine (AGPLv3) that runs a production fleet of AI agents operating two live businesses daily — with mechanical verification on every output.

  • Multi-agent orchestration
  • Python
  • Human-in-the-loop
  • Open source

• Human Design Engine

  Commercial chart-computation API and MCP server — AI capability packaged as a product that other systems and agents consume programmatically.

  • API design
  • MCP server
  • Product engineering
  • Security hardening

• BeyondSaaS.ai

  AI implementation consultancy — in-VPC, cloud, and hybrid deployments for companies that need AI working inside their own operations, with their authenticity and data sovereignty intact.

  • Fractional CAIO
  • Process reimagination
  • Workshops
  • Agentic workflows

• Production AI Infrastructure — Self-Hosted

  The self-hosted infrastructure my AI work runs on: a multi-host Proxmox cluster serving local LLM inference to a production agent fleet and two operating businesses, daily.

  • Proxmox
  • vLLM
  • GPU infrastructure
  • k3s
  • 40GbE / RDMA