Trusul vs Veritier

Trusul is a web tool for analyzing claims, comparing news coverage, asking about current events and reviewing cited evidence. Its analyzer examines credibility signals in claims, articles, messages and public URLs, including sensational wording, emotional pressure, clickbait, all-caps patterns and forceful punctuation. Reports combine a credibility score, risk verdict, explanation, evidence breakdown, warnings, missing information, limitations and cited sources. The site describes its 0–100 score as a composite drawn from three independent signals.

Compare Coverage places two reports or pieces of content side by side; differences are prompts to investigate, not proof on their own. Ask Trusul answers current-news questions in English using available citations and notes evidence and coverage limitations. For this feature, users can upload PNG, JPEG, WebP, PDF, DOCX or TXT files up to 5 MiB, processed temporarily for the request. Optional claim-verification queries may send short excerpts to Google Fact Check Tools API or NewsData.io. Plans include a free option, monthly subscriptions and one-time analysis credits, though some subscriptions and credit packs are listed as opening soon. Trusul describes itself as decision support, not a fact-checking authority.

Veritier extracts checkable claims from text, URLs, PDFs, and images, then compares them with live web evidence or private references. Results provide a verdict, confidence score, plain-language explanation, and source links. The service is available through a REST API, MCP server over Streamable HTTP, local stdio proxy, and browser interface, with parsing and OCR built into its pipeline. The attest_action endpoint checks named records such as npm, PyPI, CourtListener, SEC EDGAR, and the U.S. Code, blocking actions when records cannot be confirmed. Attestations create Ed25519-signed Claim Credentials that can be checked through JWKS and revoked; credentials remain for 400 days. Requests can use webhooks and signed retries. Free-tier text may be retained and used to improve models, while paid-tier payloads are processed ephemerally and excluded from foundation-model training. The free tier allows 25 verifications monthly; paid plans start at $19.99 a month. Verdicts and confidence scores are probabilistic.