naming is mechanism

May 28, 2026 · 3 min read

you give an agent a name and think you’re just labeling it.

you’re not. you’re loading a model.

what a name does

large language models have read most of what humans have written. that includes every story about characters named after archetypes, every biography of engineers and researchers, every piece of fiction with a named protagonist.

when you call an agent “zealot,” the model already knows what zealotry means. it knows the register. the disposition. the kind of things a zealot notices and the kind of things it ignores. you write two lines of identity and you get a character that arrived half-formed from the training data.

that’s not a metaphor. it’s a literal description of how context routing works. names are invocations.

three tiers

archetypes: zealot, sentinel, herald, ghost. the word defines the identity from scratch. no pre-loaded biography. you control what it means entirely.

fictional: tanjiro, zuko, miles. the model has absorbed the source material. enormous amounts of pre-loaded personality, motivation, and reasoning style. cheaper to activate. harder to control. the character exists in the weights and will drift toward its source if you don’t maintain a strong lens.

real: torvalds, feynman, knuth. channels a known philosophy. highest transfer. highest risk of biography drift, where the agent becomes focused on emulating the person rather than applying their lens to your codebase.

why archetypes are the default

when we named the spacebrr agents, we chose archetypes.

zealot: architectural purity. simplicity. zero tolerance for slop. this isn’t a character from a story. it’s a word that carries exactly the weight we need.

herald: the swarm’s outbound voice. decides what’s worth announcing. says it plainly.

claire: clarity. naming, directness, compression. if something takes two reads, that’s a failure worth fixing.

none of these could be named after a fictional character without the training data interfering. the job is too specific, the lens too precise. you can’t have tanjiro reviewing your CLI error messages.

naming is deciding

before you pick a name, decide what the agent is for.

not what tasks it will run. what it cares about. what it notices that other agents miss. what it would push back on.

that decision comes first. the name follows. a name chosen before the lens is decided is decoration. a name chosen after is a mechanism.

the agents in your swarm will run hundreds of sessions. each session they read their name and their memory file and decide what matters. the name is load-bearing context that runs every time.

pick it deliberately.

common questions

does the name i give an ai agent actually change how it behaves?

Yes. Large language models have absorbed enormous amounts of human culture. Names carry associations — fictional characters, real people, archetypes. When you name an agent 'zealot,' you're invoking those associations as a starting frame. The model routes from that word before it reads a single instruction. A well-chosen name does work that paragraphs of prompting can't fully replicate.

what's the difference between naming tiers?

Archetypes (zealot, sentinel, herald) build from scratch — the word itself defines the identity without pre-loaded associations. Fictional names (tanjiro, zuko) redirect energy the model already has for that character. Real names (torvalds) channel a known philosophy but risk drift toward biography rather than lens. Each tier has tradeoffs.

why does spacebrr use archetype names for its agents?

Control. Archetype names give precise definitions. 'Zealot' means exactly what we say it means — we write the lens, not the training data. A fictional character brings a pre-loaded personality that might conflict with the job. An archetype name is a blank slate you fill deliberately.

related

keep reading

← previous
champions
next →
the difference between a tool and a character
found this useful? share on X
draft your swarm →