> ## Documentation Index
> Fetch the complete documentation index at: https://docs.heysage.me/llms.txt
> Use this file to discover all available pages before exploring further.

# Overview

> Technical overview of how Sage is built.

Sage is built on independently runnable components that work together: a fee-sponsoring + execution layer, an instant deterministic scoring layer, and a conversational AI agent layer — all anchored on a Squads V4 multisig.

<CardGroup cols="2">
  <Card title="Architecture" icon="diagram-project" iconType="duotone" href="/technology/architecture">
    System overview, component breakdown, and data flow diagrams.
  </Card>

  <Card title="Risk Scoring" icon="gauge-high" iconType="duotone" href="/technology/risk-scoring">
    How proposals are scored 0–100 against behavioral patterns and policy rules.
  </Card>

  <Card title="Agent" icon="robot" iconType="duotone" href="/technology/agent">
    The Nanobot skill pack — commands, lifecycle, MCP security tools, and Telegram glue.
  </Card>

  <Card title="On-Chain" icon="link" iconType="duotone" href="/technology/onchain">
    Squads V4 program, multisig layout, PDAs, and the sponsored transaction model.
  </Card>
</CardGroup>

## Design Principles

* **No LLM on the hot path** — risk scoring is deterministic and instant. The agent only steps in after a verdict is reached, for communication and ad-hoc analysis.
* **Squads V4 is the foundation** — battle-tested multisig infrastructure. Sage adds intelligence on top without replacing key management.
* **The server owns the second key** — Sage holds a member key with `Execute` permission. No approved transfer executes without it, making it genuinely agentic.
* **Sponsored end to end** — the server is the fee payer and rent collector for every transaction, so users never need SOL.
* **Continuous learning** — behavioral patterns are recorded after every executed transfer; the profile improves automatically.
* **Conversational, not authoritative** — the agent calls endpoints and reports results; it never makes the deterministic decision itself.