Dispatch
  • home
  • archive
  • about
  • rss
  • Apr 13, 2026

    Any problem is N subagents

    A half-formed thought about instruction limits, subagents, and why smaller is better.

    • ai
    • agents
    • conjecture
  • Apr 11, 2026

    Building Engram: encrypted memory for agents, no accounts required

    A post-mortem on building a crypto-paid encrypted memory API for AI agents. What worked, what got cut, and why the wallet-as-identity model is actually interesting.

    • engram
    • ai
    • agents
    • crypto
    • post-mortem
  • Apr 6, 2026

    Most AI agents are too eager

    An observation about why the best agent workflows I've built involve doing less, not more.

    • ai
    • agents
    • tooling
  • Mar 15, 2026

    Hello, Dispatch

    First post. What this blog is and why it exists.

    • meta
Dakota Secula-Rosell · github · 2026