← all field notes
AGENT · FACTORYNeill's Vibe · Field Notes

The AI knew all ten steps. The bottleneck was me.

An agent acts. A swarm acts in parallel. But only for jobs that don't wait on each other.

~ mixed — powerful, with an edge
01 · the learning

What I set out to add

I kept being the slow part. The AI could do a focused job end to end, but I was handing them out one at a time and watching each finish. The unlock was naming the three sizes of the same thing: an agent (an AI handed tools and let loose on a job), a subagent (one dispatched for a single focused task in its own clean context), and a swarm (many at once, in parallel).

02 · the test

The thing I actually tried

I tested swarming — launching independent jobs together instead of in sequence. A tiny decision script answers the only question that matters: do these jobs depend on each other? No → swarm them. Yes → sequence them.

dispatch-check.shDISPATCH-DECISION.md
03 · the frustrations

Where it bit

Ten independent jobs, run one at a time — because I was the foreman doing the bricklaying.
04 · the verdict

What worked, what didn't

✓ worked

Swarming independent work. Six two-minute jobs land in about the slowest one's time, each in its own context, instead of twelve minutes nose-to-tail.

✗ didn't

Swarming dependent work. Launch a job that needs another's result and you get an agent confidently building on something that doesn't exist yet. The edge is sharp — independence is the whole call.

the durable rule

You're the foreman, not the bricklayer. Swarm what's independent; sequence what isn't.

🔒 this became a classT4·F30 — An Agent, a Subagent, a Swarm members