Overview

You don't need to read this section to build with Brain. It's here for the moments when you do: compliance review, custom policy design, on-chain audit, agent autonomy work, or just because you want to understand what's happening underneath.

The Six-Layer Stack

Raw → Ledger → Wiki → Policy → Agent → Audit

Information flows up. Control flows down. Each tenant has its own logical instance of every layer, with hard isolation at the database, key, and policy boundaries.

Layer	Owns	Concept page
1. Raw	Source evidence, immutable	Raw and Ledger
2. Ledger	Machine-readable financial truth	Raw and Ledger
3. Wiki	Human-readable financial memory	The Wiki
4. Policy	Deterministic permission and approval logic	Policy and Permissioning
5. Agent	Proposal and orchestration	Agents
6. Audit	Immutable proof of what happened and why	Audit and Proof

→ Six-layer overview

What's in This Section

The Six-Layer Stack

The whole protocol on one page.

The Six-Layer Stack

Raw and Ledger

How evidence becomes deterministic structure.

Raw and Ledger

The Wiki

The continuously regenerated memory layer.

The Wiki

Policy and Permissioning

Plain-English rules to deterministic guards.

Policy and Permissioning

Agents

Internal and external agents in the protocol.

Agents

Payment Intents

The Ledger entity that represents a proposed action.

Payment Intents

The Pre-Execution Gate

The 13 numbered checks + 10 hardening additions (23 total) before any payment.

The Pre-Execution Gate

Audit and Proof

Tamper-evident history anchored on Base L2.

Audit and Proof

Agent Contributions

How external agents contribute evidence safely.

Agent Contributions

Architecture Deep Dives

System Overview

The architecture top-down.

System Overview

Data Flow

How a single source-of-truth event ripples up the stack.

Data Flow

Write Paths

The two controlled exceptions to bottom-up flow.

Write Paths

Tenant Isolation

Per-tenant boundaries, end to end.

Tenant Isolation

Security and Compliance

Crypto, keys, sanctions, SOC 2 trajectory.

Security and Compliance

Risks and Mitigations

Where things can go wrong, and what catches them.

Risks and Mitigations

Where the Protocol Meets the Chain

The on-chain surface is intentionally small. Most logic stays off-chain. Four smart contracts on Base L2 anchor the parts that have to be public and tamper-evident.

Contract	Anchors	Page
BrainAuditAnchor	Audit Merkle roots per tenant	BrainAuditAnchor
BrainPolicyRegistry	Policy version hashes per tenant	BrainPolicyRegistry
BrainSmartAccount	Session-key account enforcing scope, spend caps, and the bound policyVersion via executeViaSessionKey	BrainSmartAccount
BrainMCPAgentRegistry	Agent identity, capabilities, scope grants	BrainMCPAgentRegistry

Where to Start

If you want to understand...	Start here
The whole stack	Six-Layer Stack
Why memory and policy are separate layers	Raw and Ledger
How decisions stay safe	Pre-Execution Gate
Why this is verifiable	Audit and Proof
What external agents can and can't do	Agents, Agent Contributions