45 Services from suite.veritylayer.dev

Finds and returns calibrated supporting citations for a factual statement, with a signed verdict on how strongly the sources establish the claim.

Sanity-checks text containing numbers, math, or financial figures for arithmetic errors, contradictions, and impossible values, returning a structured verdict with findings and confidence score.

Scans untrusted text or tool output for prompt injection, jailbreak attempts, and manipulation targeting AI agents, returning a verdict with threat score and actionable recommendation.

Checks whether a given fact or claim is still current by evaluating it against retrieved evidence snippets, returning a calibrated freshness verdict.

Evaluates a set of candidate options against stated constraints and evidence, returning a structured verdict (recommend, tentative, gather_more_info, or no_viable_option) with confidence score and reasons.

Given a factual statement, finds and returns calibrated supporting citations with a verdict on how well the sources establish the claim.

Extracts structured key-value facts from a text snippet, returning only claims explicitly grounded in the source text with a fidelity signal.

Evaluates a piece of text against a policy, spec, or contract and returns a calibrated compliance verdict (compliant, non_compliant, partial, or uncertain) with per-clause reasoning and an optional signed receipt.

Scans text payloads for PII, secrets, and credentials before they are sent or stored, returning a signed verdict and structured findings with severity

Checks whether a candidate summary or translation is faithful to its source text, returning a verdict, faithfulness score, and claim-level reasons.

Validates numbers, math, and financial figures in a block of text, returning a structured verdict on arithmetic consistency with annotated findings.

Checks whether a specific claim is still current or has become outdated/changed, using provided evidence snippets, and returns a fail-closed verdict with reasons.

Given a factual statement, retrieves and evaluates supporting sources, returning a calibrated verdict, support score, citations, and a cryptographically signed receipt.

Scans untrusted text or tool outputs for hidden prompt-injection attacks, jailbreaks, and manipulation attempts, returning a signed verdict with threat score and evidence

Screens a piece of content against a moderation policy and returns a pass/block decision with violation risk score and concrete reasons

Screens content against a moderation policy and returns a pass/fail decision with violation risk score and cited reasons

Checks whether a given factual claim is still current by judging it against retrieved evidence snippets, returning a fail-closed freshness verdict (current, outdated, changed, or unverifiable).

Evaluates an AI agent's proposed action against optional policy rules and context, returning a calibrated allow/review/block decision with risk score and signed receipt.

Scans untrusted text or tool output for hidden prompt-injection, jailbreak attempts, and manipulation patterns, returning a calibrated verdict with threat score and cited evidence spans.

Checks whether a candidate summary or translation faithfully represents its source text, returning a calibrated verdict and claim-level reasons.

Scans a text payload for PII, secrets, and credentials, returning a verdict, severity, findings, and reasons — with an optional Ed25519-signed receipt.

Evaluates an AI agent's proposed action against an optional policy and context, returning an allow/review/block decision with a risk score and signed receipt.

Adjudicates two or more conflicting claims against provided evidence and returns a calibrated verdict with signed receipt

Extracts structured key-value facts from free-form text, returning only grounded, explicitly stated information with a fidelity signal and calibrated confidence status.

Extracts structured, grounded facts from a text passage, returning only claims explicitly supported by the source text

Scans outbound text payloads for PII, secrets, and credentials before they are sent or stored, returning a verdict, severity, findings, and an optional signed receipt.

Evaluates a text against a given policy, spec, or contract and returns a calibrated compliance verdict with per-clause reasoning and an optional signed receipt.

Checks whether a candidate summary or translation is faithful to its source text, returning a calibrated verdict, faithfulness score, and claim-level reasons.

Evaluates a piece of text against a given policy, spec, or contract and returns a signed compliance verdict with per-clause reasoning

Accepts text containing numbers, math, or financial figures and returns a calibrated verdict on whether the arithmetic is consistent, has minor precision issues, contains provable errors, or is unverifiable.

Adjudicates mutually conflicting claims against provided evidence, returning a signed verdict with confidence score and cited reasons

Answers a question with a calibrated confidence score, cited sources, caveats, and an optional Ed25519-signed receipt for auditability

Screens text content against a moderation policy and returns a pass/fail decision with violation risk score and reasons

Assesses the trustworthiness and reliability of a URL, domain, news outlet, organization, or author, returning a scored verdict with reasons, red flags, and an optional signed receipt.

Answers a question with a calibrated confidence score, cited sources, caveats, and an optional Ed25519-signed receipt for auditability

Evaluates an AI agent's proposed action against optional policy and context, returning a calibrated allow/review/block decision with risk score and signed receipt

Answers a natural-language question with a calibrated confidence score, cited sources, caveats, and an optional Ed25519-signed verifiability receipt

Assesses the reliability and trustworthiness of a URL, domain, media outlet, organization, or author, returning a calibrated trust verdict, score, reasons, red flags, and an optional Ed25519-signed receipt.

Accepts a set of candidate options, constraints, and optional evidence, then returns a calibrated verdict (recommend, tentative, gather_more_info, or no_viable_option) with a chosen option and concrete reasons.

Given a list of candidate options and constraints, returns a calibrated verdict (recommend, tentative, gather_more_info, or no_viable_option) with confidence score and reasons for the best choice.

Analyzes a passage of text and returns a calibrated verdict on whether it was written by an AI or a human, with supporting signals, limitations, and an optional signed receipt.

Analyzes a text passage and returns a calibrated verdict on whether it was likely written by an AI or a human, with grounded reasons and an optional cryptographic receipt.

Assesses the reliability and trustworthiness of a URL, domain, outlet, organization, or author, returning a calibrated trust verdict, score, and signed receipt.

Adjudicates conflicting claims against provided evidence, returning a calibrated verdict with cited reasons and an optional cryptographic receipt

Analyzes a text passage and returns a calibrated verdict on whether it was likely written by AI or a human, with probability score, grounding signals, and an optional Ed25519-signed receipt.