# 5.2 PTERI for AI Authority

PTERI treats AI agents as **principals**, not tools.

A principal must have:

* Identity
* Authority
* Limits
* Accountability

#### With PTERI

AI agents gain:

* **Cryptographic identities**
* **Explicit authority** via signatures
* **Scoped permissions**
* **Revocable access**

And they lose:

* Static secrets
* Implicit trust
* Silent escalation

***

#### The new model

Instead of asking:

> “Does this API key work?”

Systems ask:

> “Does a valid signature exist for this exact intent?”

An AI agent:

1. Requests an action
2. Receives a scoped challenge
3. Obtains explicit authorization
4. Executes only what was approved

No signature → no action.

***

#### Why this matters

This model ensures:

* Every AI action is attributable
* Every action has provable intent
* Authority can be limited and revoked
* Abuse is cryptographically detectable

AI becomes **auditable**, not just powerful.

***

<figure><img src="/files/UUpkGz7FC4lG86wWbmP3" alt=""><figcaption></figcaption></figure>


---

# Agent Instructions: 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:

```
GET https://docs.kakrlabs.com/5.-ai-agents-and-mcp-integration/5.2-pteri-for-ai-authority.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.