Architecture Overview

QWED architecture for deterministic verification of LLM outputs and AI agent actions using formal methods, policy guards, and signed attestations.

This page gives the high-level architecture.
For deeper diagrams, see Architecture Diagrams.

QWED separates untrusted model translation from deterministic verification so you can enforce AI reliability, tool call verification, and zero-trust policy boundaries at runtime.

Core principle

Translation is useful but untrusted. Verification is the trust anchor.

Layered architecture

1) API Gateway

• Authentication and authorization
• Rate limiting and tenancy controls
• Request routing and transport security

2) Translation Layer (untrusted)

• Converts natural language into structured inputs
• Can use any LLM provider (cloud or local)
• Output is always treated as untrusted until verified

3) Verification Engines (deterministic)

Engine	Purpose
Math	Symbolic arithmetic and algebra checks
Logic	SAT/SMT verification and constraint solving
Code	AST and symbolic security analysis
SQL	Query safety and structure validation
Schema/Taint/Graph/Stats/Fact/Image/Reasoning	Domain-specific verification paths

4) Agent security guards

Guards inspect tool calls, contexts, and policy boundaries before execution.

Guard	Purpose
RAGGuard	Defends retrieval contexts from injection/poisoning
ExfiltrationGuard	Prevents unauthorized data movement
MCPPoisonGuard	Validates MCP tool definitions and safety
SovereigntyGuard	Enforces data residency and routing policy
SelfInitiatedCoTGuard	Checks reasoning flow integrity
ProcessVerifier	Milestone-based process validation
StateGuard	Deterministic workspace rollback via shadow git snapshots

5) Attestation and audit

Each verification can emit signed evidence for traceability and compliance workflows.

{
  "query_hash": "sha256(...)",
  "verification_result": true,
  "engine": "QWED-Math-v2",
  "timestamp": 1735689600
}

Request lifecycle

Security model snapshot

Threat	QWED response
Hallucinated claim	Rejected or corrected by deterministic check
Prompt injection	Translation may be affected, but verifier/guards enforce policy
Unsafe code or SQL	Blocked by parser, AST checks, and guard rules
Untrusted tool action	Guarded and policy-checked before execution

Related verification guides

LLM verification

See how QWED validates LLM outputs with formal methods instead of probability-only confidence.

AI agent verification

Apply policy enforcement and pre-execution checks to autonomous agents.

Prompt injection defense

Review production guidance for prompt injection defense and OWASP LLM risks.

MCP security

Secure Model Context Protocol integrations and verify tool execution paths.

Deployment modes

Mode	Fit
Cloud API	Fastest start, hosted control plane
Self-hosted	Data control in your VPC/Kubernetes
Hybrid	Mix cloud scale with local policy boundaries

Next steps

1. Core Concepts
2. Architecture Diagrams
3. SDK Guards
4. Self-Hosting