broomva.tech

Reliability engineering for complex systems.

  • Pages
  • Home
  • Projects
  • Writing
  • Notes
  • Tools
  • Chat
  • Prompts
  • Link Hub
  • Social
  • GitHub
  • LinkedIn
  • X

Writing

Canonical long-form notes from real implementation work: architecture decisions, tradeoffs, and operating models.

Rocket Simulation Meets Recursive Improvement

We turned OpenRocket into a headless simulation engine, built a CLI tool, and ran 144 EGRI optimization trials in 5 minutes. Here is what we learned about mutation surfaces.

March 19, 2026

Autonomous Development Workflows: A Storyboard Guide to the Control Metalayer and bstack

From zero to autonomous — a step-by-step storyboard for enabling self-operating development workflows using the Broomva Stack, the agentic control kernel, and Symphony orchestration.

March 18, 2026

The Control Metalayer: How Agents Learn, Remember, and Govern Themselves

A control-systems framework that gives AI coding agents persistent memory, behavioral governance, and progressive knowledge crystallization across sessions.

March 18, 2026

The Integration

Most people keep work separate from fitness separate from relationships. I see one life — the same rigor applies everywhere.

March 18, 2026

How FIFA World Cup 2026 Host Committees Are Using an AI Agent to Process Thousands of Procurement Requests

An AI-powered vendor interest agent is handling procurement intake at scale for FIFA 2026 host cities — replacing static forms with conversational workflows that actually work.

March 17, 2026

Autonomous Repos Are Control Systems

The repository is not just where code lives. It is the control surface for autonomous software development.

March 12, 2026

Turning a Personal Site into a Codex PR Content Engine

A lightweight operating model where humans steer weekly priorities and agents execute content and UI improvements through guarded PRs.

February 18, 2026

Reliable Agentic Systems Need Better Harnesses

The harness around an LLM determines whether agent workflows are shippable under real production constraints.

February 16, 2026

Interface as an Operating Surface for Agents

AI interfaces should expose intent, status, and control points so operators can steer execution with confidence.

February 12, 2026