Skip to main content
QWED v6.0.0 is now live — Trust boundary completion: unified DiagnosticResult schema across all /verify/* endpoints, mandatory control-plane attestation, and deterministic proof_ref guarantees. See what’s new →

​
What is QWED?

QWED (Query With Evidence & Determinism) is a trust boundary for AI systems:
  • LLMs can translate user intent into structured claims.
  • QWED verifies those claims with deterministic engines before execution or response.
  • You get proof-backed outcomes instead of probability-only confidence.
QWED is designed for LLM verification, AI agent security, verified tool calls, prompt injection defense, and deterministic transaction verification in high-stakes workflows.
“Do not trust generated output. Verify it.”

​
Explore common verification problems

LLM verification

Learn how formal verification for LLMs differs from prompting, RAG, and output formatting.

AI agent security

Add pre-execution checks, policy enforcement, and budget controls for agent actions.

Prompt injection defense

Harden your stack against prompt injection, exfiltration, and unsafe execution paths.

MCP security

Secure Model Context Protocol tools with deterministic verification and tool schema checks.

​
When to use QWED first

Math and logic

Verify equations, constraints, and logical claims before they reach users.

Code and SQL

Catch unsafe patterns, injection risks, and structural errors before execution.

Agent tool calls

Inspect actions and payloads before external systems are touched.

High-stakes workflows

Add deterministic checkpoints for finance, legal, tax, and regulated systems.

​
Quick start (5 minutes)

1

Install and configure

Follow Installation and set your provider with LLM configuration.
2

Run first verification

Use Quick start to validate math, logic, code, and SQL.
3

Integrate into production flow

Use Integration getting started and Production deployment.

​
Verification engines at a glance

Math

SymPy-based symbolic verification.

Logic

Z3 SAT/SMT verification with models.

Code

AST and symbolic checks for risky behavior.

SQL

Parser-backed SQL safety and validation.

Schema

Type and shape validation for structured outputs.

Taint

Data-flow tracking for untrusted inputs.

See all engines

Explore core, analysis, and specialized engines.

​
What’s new in v6.0.0

Trust Boundary Completion

All 12/12 sub-issues closed in Epic #263. Every /verify/* API pathway returns DiagnosticResult and routes through mandatory enforce_trust_decision. VERIFIED is a protocol guarantee backed by a non-empty, deterministic proof_ref. Learn more →
Observation vs Admission architecture codified: /verify/* endpoints return the 3-layer DiagnosticResult (status / agent_message / developer_fields / proof_ref). Learn more →
LogicVerifier and FactVerifier migrated to DiagnosticResult with attestation-backed verdicts and advisory checks.
Developer fields snapshotted recursively to prevent alias windows in enforce_trust_decision, and VerificationCache key namespacing by normalized tenant_id.
  1. Core concepts
  2. Architecture overview
  3. SDKs overview
  4. API overview
  5. Integration guide