Verification engines

​

Engine overview

​

Deterministic-first philosophy

1. Try deterministic methods first (100% reproducible)
2. Fall back to LLM only when necessary
3. Discount LLM confidence when used

# Example: fact verification is deterministic
result = client.verify_fact(
    claim="Paris is in France",
    context="Paris is the capital of France."
)
# Uses TF-IDF similarity + entity matching
# No LLM needed for most claims

See Determinism guarantee for the full engine classification and how to check if a response is SYMBOLIC or HEURISTIC.

​

Engine selection

result = client.verify(query, type="math")

​

Engine documentation

​

Deterministic engines

• Math engine — calculus, matrix, financial
• Logic engine — quantifiers, theorem proving
• Schema engine — JSON structure & math

​

Security engines

• Code engine — multi-language security
• SQL engine — complexity limits
• Taint engine — data flow analysis

​

Data verification engines

• Stats engine — Wasm sandbox execution
• Fact engine — TF-IDF + citations
• Graph engine — knowledge graph triples
• Image engine — deterministic verification

​

Orchestration engines

• Reasoning engine — multi-LLM validation
• Consensus engine — parallel execution