AI-native architecture

Built for agents. Usable by humans.

Volentia is a resident operating system where MCP tools are the primary API, LLMs are a runtime primitive, and the dashboard is a thin client over the same tools your agents call.

1. Tool layer (MCP)

Every capability is an MCP tool

Cases, bookings, rent, contracts, journeys, documents, and communications use typed, versioned, RLS-scoped schemas. Resident, operator, and external agents call the same tools.

2. Reasoning layer

LLMs as a runtime primitive

Triage, categorisation, sentiment, translation, drafting, and journey decisions run through models by default. Prompts are versioned and evaluated like code.

3. Agent layer

Jeeves and your own agents

Jeeves is the built-in resident and operator concierge. ChatGPT, Claude, Cursor, or an in-house agent connects to the same MCP endpoint with per-user OAuth.

4. Interop layer

MCP in, MCP out

Register external MCP servers for work orders, calendars, or energy providers and Volentia agents call them alongside native tools.

5. Identity and safety

Per-user authentication, end to end

Supabase OAuth 2.1 supports dynamic client registration. Every tool call runs as the authenticated user under database RLS, and mutating tools require explicit approval.

6. UI layer (fallback)

A dashboard for humans

The web app is a thin client over the tool layer. Use clicks when you prefer them and prompts when you do not.