> For the complete documentation index, see [llms.txt](https://docs.epiora.xyz/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.epiora.xyz/execution-architecture.md).

# Execution Architecture

Epiora separates intent, transaction construction, authorization, and execution.

This separation is central to the security model.

The system recognizes multiple execution origins.

### Manual execution

For ordinary browser users: 

```
Intent
  |
  v
Transaction preparation
  |
  v
Review
  |
  v
User confirmation
  |
  v
Wallet signature
  |
  v
Execution
```

The user wallet remains the authorization boundary.

A model-generated response does not constitute approval.

A prepared transaction does not constitute approval.

A review screen does not constitute approval.

Execution requires the appropriate wallet authorization.

## Agent-Assisted Execution

Agent-assisted actions follow the same principle.

```
User request
     |
     v
Agent interpretation
     |
     v
Deterministic action
     |
     v
Review
     |
     v
User authorization
     |
     v
Execution
```

The Agent can assist with understanding and constructing an action.

It cannot convert probabilistic model output into transaction authority.

This allows Epiora to use AI without making AI itself the security boundary.

## Remote and Automated Execution

Epiora's architecture also supports controlled remote and strategy-oriented execution paths.

These paths use a stricter authorization model.

Conceptually:

```
Tool request
    |
    v
Execution context
    |
    v
Wallet identity
    |
    v
Policy enforcement
    |
    v
Signing callback
    |
    v
Broadcast gate
    |
    v
Execution
```

Remote execution does not silently fall back to a manual wallet or unrestricted signer.

Strategy wallets remain isolated from primary wallet identities.

Broadcast controls provide an additional kill switch, while wallet policies remain the cryptographic authorization layer.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.epiora.xyz/execution-architecture.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.