SMERESKI
  1. PROJECTS
  2. RESUME
  3. BLOG
  4. CONTACT

POST · 2026-04-22

2026-04-22 · 4 MIN READ

Swarms that ship

Three rules for running a small army of AI agents end-to-end without burning the house down.

aiprocess

There is a version of agent orchestration where you sit and watch a prompt loop forever and call it work. Skip that version. The shape that ships looks like a small org chart: one coordinator, a handful of specialists, tight role boundaries, and a checkpoint after every task. Agents that report nothing get nothing back. Agents that commit progress to shared memory get rehired.

Rule one: phase the work. Specification, pseudocode, architecture, refinement, completion. Each phase has a tight contract and a single output the next phase can consume. Skipping phases is faster on the way down and slower at the bottom of the well.

Rule two: humans review the diffs, not the chatter. The interesting artifact is always the patch. If you find yourself reading agent transcripts to understand what changed, the agents are writing the wrong things to memory.

Rule three: keep the gaming card out of the AI lane. Two mid-range cards that stay out of each other's way beat one big card that is always being preempted by something rendering frames. Boring infrastructure, boring deploys, interesting work in the middle. That is the whole arc.

REFERENCES3 LINKS
  • 01
    claude-flow

    Coordinator and hive-mind tooling powering the swarm.

    https://github.com/ruvnet/claude-flow

  • 02
    agentic-flow

    Underlying agent runtime claude-flow extends.

    https://github.com/ruvnet/agentic-flow

  • 03
    SPARC methodology

    Specification → Pseudocode → Architecture → Refinement → Completion.

    https://github.com/ruvnet/claude-flow#-sparc-development-methodology