> For the complete documentation index, see [llms.txt](https://axon-finance.gitbook.io/axon-finance-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://axon-finance.gitbook.io/axon-finance-docs/part-iii-technical-architecture/part3-architecture.md).

# Intro: Building Determinism into the Foundation

Building determinism into the foundation

> The hardest thing about a payment chain isn't throughput — it's determinism, authorization, and recovery.

Part I and Part II argued **why** you need an L1 built for PayFi + AI-agent payments. This part answers **how to build it**.

We take AXON's technical design apart from the top down: from the foundational argument for "why a purpose-built L1 is unavoidable," to a panorama of the five-layer architecture, and then layer by layer through consensus, payment finality, price-feed safety, the compliance gateway, and account abstraction.

The chapter map for this part:

* **3.1** Why a Purpose-Built L1 — four reasons that cannot be sidestepped.
* **3.2** The Five-Layer Architecture — a payment's journey from the top down.
* **3.3** Consensus, Sub-Second Finality & Performance Targets — and how we treat performance numbers honestly.
* **3.4** Payment Finality & Double-Spend Prevention — the hardest thing a payment chain does.
* **3.5** Stablecoins & Price Feeds — multi-source validation and deviation circuit breakers.
* **3.6** Pluggable Compliance Gateway — building compliance into the foundation.
* **3.7** Account Abstraction, Session Keys & Paymaster — laying the primitives for AI-agent payments.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://axon-finance.gitbook.io/axon-finance-docs/part-iii-technical-architecture/part3-architecture.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.