Independent engineering journalThinking in public / 2026

The writing index

Investigations, ideas, & field notes.

What I am learning from agent systems, enterprise AI adoption, harness engineering, OpenClaw experiments, and engineering leadership.

All writing.

7 notes

  1. Agent Systems

    OpenClaw Concurrency Is Not Isolation

    My investigation into why concurrent OpenClaw sessions can still compete for shared runtime resources.

    3 min read
  2. Enterprise AI

    Skill-Defined Tools vs Runtime-Provided Tools in Enterprise Agent Platforms

    A platform architecture note on why skills can describe tool usage, but runtimes must own executable capabilities.

    3 min read
  3. Enterprise AI

    Building SOP Retrieval for OpenClaw Skills Instead of Prompt-Stuffing

    A design note on separating OpenClaw skill workflow from SOP retrieval, search quality, and business policy ownership.

    4 min read
  4. Enterprise AI

    OpenClaw Permissions: Why Prompt Rules Are Not Enforcement

    An investigation into why prompts guide behavior but runtime approval systems are needed for real enforcement.

    4 min read
  5. Agent Systems

    Agent Loops vs Agent Teams: Understanding Where Intelligence Actually Lives

    A practical distinction between agent loops, agent teams, execution style, topology, and where orchestration should own control flow.

    3 min read
  6. Agent Systems

    Investigating Honcho Memory Architecture for OpenClaw

    Notes on Honcho representations, observe_me, memory quality, and how long-term memory should be applied in OpenClaw.

    2 min read
  7. Engineering Leadership

    Becoming AI-Native: Rethinking How Organizations Work

    A reflection on why AI adoption is less about tool access and more about organizational design, harness engineering, governance, and leadership judgment.

    4 min read