teams.sgit.ai / topologies

The three topologies

The estate contains three staffed teams using the same role names with different mandates, and the naming is Wardley's: Explorer (pioneer), Villager (settler), Town Planner. This is Pioneers–Settlers–Town Planners implemented as agent configurations rather than drawn as a diagram — and as far as the commissioning pack can determine, nobody else has published this. It should be, and is, this site's second most important page.

For Pioneers–Settlers–Town Planners itself — the evolution axes, the model in general — wardley-maps.sgit.ai owns the material. This page owns only the staffing of it as three agent teams, which is original.

What each team is for

ExplorerVillagerTown Planner
MandateBuild the new thingHarden what existsIndustrialise and capitalise
Roles17 dirs / 13 defined17 / 174 / 3
Governing ruleDiscover"Harden, do not build"Classify and fund
On a needed redesignDo itSend it back to Explorer

Villager — the mandate, in the role files' own words

Not inferred — stated in the role files themselves:

The code works. Your job is to make it work reliably under production conditions.
— Villager Dev, team/villager/roles/dev/ROLE.md
Preserve behaviour exactly — every change must produce identical outputs for identical inputs. If behaviour changes, send it back to Explorer.
— Villager Dev
User experience is frozen — the UX as delivered by Explorer is what ships. No additions, no changes.
— Villager Designer
Harden, do not redesign — security architecture is frozen from Explorer. Harden what exists. If a redesign is needed, send it back.
— Villager AppSec

And the corresponding exclusions, in the role files' own phrasing:

Do NOT design new UX features — send to Explorer.
— Villager Designer, Not Responsible For
Do NOT redesign security architecture — that's Explorer territory.
— Villager AppSec, Not Responsible For

Town Planner — a sketch, not a template

Small and commercial: the Accountant "provides the financial models and projections that the Alchemist wraps in investor narrative," with the Cartographer supplying "maturity classification (Genesis/Custom/Product/Commodity) and Wardley map financial flows" — the evolution axis reappearing as the thing that decides which team owns a component.

Publish it as a sketch. Four directories, three definitions, its Librarian missing, and its content is investor-facing rather than operational. This site does not write the missing Librarian for it.

Why this solves a real problem

The failure mode in multi-agent systems is not incapacity; it is an agent improving something it was asked to preserve. A capable model handed hardening work will notice a better design and implement it, and the result is a system that never stabilises because every pass rewrites the previous one.

The Villager mandate is a refusal engineered into the role: preserve behaviour exactly, and when you see something better, hand it back rather than build it. That is a genuinely hard instruction to give a capable generalist, and writing it into the role definition — with the destination named — is what makes it stick.

The handback path is the mechanism. A topology without a defined return route is just a label; here, every freeze rule names where the work goes instead.

The handback rules, as a table

Frozen in VillagerWhere a needed change goes
Behaviour / outputsSend back to Explorer if a change is needed
User experienceSend back to Explorer — no additions, no changes
Security architectureSend back to Explorer — Villager hardens, never redesigns

The same role, three ways

Designer is the best single example, existing in all three teams: creating UX in Explorer, guarding frozen UX in Villager, and shaping investor-facing material in Town Planner. One page, showing one role's three definitions →

The honest caveats