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

# Execution Levels

> What an agent can do, as capability tiers granted through its server-owned tool profile and token scopes — Read, Prepare, Execute, and Governed Autonomous.

An agent's capability is not a build-time flag it holds — it is a **level granted server-side** through the tool profile bound to the agent and the scopes minted into its short-lived token. Raising an agent's level widens the tool surface it can reach; it never widens the authority [policy](/core-concepts/policy-gates) grants. Every level above Read still clears the policy engine and, for signing, [MPC threshold signing](/mpc/signing-intents).

## The four levels

| Level                        | Capability                                                                                                                                                                | Tool profile · scopes       | Reference                                                     |
| ---------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------- | ------------------------------------------------------------- |
| **R0 · Read**                | Balances, holdings, prices, fee estimates, asset/chain resolution, tx status & history, wallet inventory                                                                  | `read`                      | [Tool Reference](/ai-agents/tool-reference)                   |
| **R1 · Prepare**             | Unsigned transfers, swap quotes & simulations, fee/nonce/slippage preparation, external-signer / approval handoff                                                         | `prepare`                   | [Tool Reference](/ai-agents/tool-reference)                   |
| **R2 · Execute**             | Hosted MPC signing composed with the policy engine, exact payload-bound one-use signing intents, idempotent broadcast and finality reconciliation                         | `execute` · `wallets:sign`  | [Signing Intents](/mpc/signing-intents)                       |
| **GA · Governed Autonomous** | Per-agent policy, atomic cumulative budgets and reservations, destination/asset/chain/contract/method controls, durable approvals, emergency controls, execution receipts | `governed` · `wallets:sign` | [Managing Policy Rules](/core-concepts/managing-policy-rules) |

All four levels are available now. A level is the tool profile you bind to an agent plus the scopes you request at [token exchange](/ai-agents/token-exchange) — nothing to install, nothing to self-operate.

## R0 · Read

The read-only floor. The `read` profile exposes balances, holdings, prices, fee estimates, asset and chain resolution, transaction status and history, and wallet inventory. No signing scope is present, so no signing tool is reachable regardless of policy. R0 is the safe default for reporting and monitoring — see the [Reporting & Treasury Insights template](/ai-agents/templates/reporting-treasury-insights).

## R1 · Prepare

Everything in R0 plus construction of unsigned artifacts: unsigned transfers, swap quotes and simulations, and fee, nonce, and slippage preparation. R1 also covers external-signer and approval handoff — the agent produces a payload for a signer it does not control. Still no `wallets:sign`, so R1 cannot release a share.

## R2 · Execute

Adds `wallets:sign`. The agent drives hosted MPC signing composed with the [policy engine](/core-concepts/policy-gates): each execution binds to an exact, one-use [signing intent](/mpc/signing-intents), and broadcast is idempotent with finality reconciliation.

<Note>
  The `wallets:sign` scope enables the tool; the policy engine still decides — a denied intent cannot be signed. See [Policy Gates → What a Deny Does](/core-concepts/policy-gates#what-a-deny-does).
</Note>

## GA · Governed Autonomous

The full governed surface for autonomous operation: per-agent policy, atomic cumulative budgets and reservations, destination/asset/chain/contract/method controls, durable approvals, emergency controls, and execution receipts. The agent operates under its mandate and budget — defined in [Agents and Authority](/core-concepts/agents-and-authority) and set by an admin via [Managing Policy Rules](/core-concepts/managing-policy-rules) — with durable receipts in the [audit trail](/security/audit-trail).

## What sets an agent's capability

An agent's capability is the **tool profile an admin bound to it** — `read`, `prepare`, `execute`, or `governed` — set on WalletSuite's side, never by the caller. The short-lived token the agent connects with can never exceed that profile: a capability the profile does not grant cannot be reclaimed by the model, the prompt, or a downstream call.

Chains follow the same rule — an agent can only act on the chains it's entitled to. See [Policy Gates](/core-concepts/policy-gates).

## Related

<CardGroup cols={2}>
  <Card title="Agents & Authority" icon="user-shield" href="/core-concepts/agents-and-authority">
    Identity, wallet grant, mandate, budget, and expiry — the five bound things.
  </Card>

  <Card title="Policy Gates" icon="shield-check" href="/core-concepts/policy-gates">
    The deterministic decision point every level above Read passes through.
  </Card>

  <Card title="Tool Reference" icon="wrench" href="/ai-agents/tool-reference">
    The tools each profile exposes.
  </Card>

  <Card title="Token Exchange" icon="key" href="/ai-agents/token-exchange">
    How scopes and tool profile reach the agent as a short-lived token.
  </Card>
</CardGroup>