Our Intelligence Brief

Scrapers extract.
Litmus interprets.

When your agent scrapes a page, it gets text back — but text alone doesn't say whether that text is worth trusting. Was this written yesterday or five years ago? Is this the original source, or a copy of a copy sitting three syndication hops away from the truth? Is this the whole article, or the first three paragraphs before a paywall cuts it off?

Litmus answers those questions on every single parse, automatically. It reads the page the way a skeptical researcher would, then hands your agent a short, plain-language brief instead of making your agent guess and burn up tokens.

Litmus is heuristic, not model-based. Most "trust" layers on competing tools work by calling another LLM to judge the content, which just stacks a second hallucination risk on top of the first. Litmus can't hallucinate its own metrics — every signal is computed with deterministic rules at the edge. Your agent gets a second opinion on whether to trust the data, instantly, with no extra LLM call and no extra hallucination risk. Scrapers extract. Litmus interprets.

Trust & Provenance

Source Authority

Every domain scored and classified — government, academic, news, forum, social. Your agent ranks sources before it reads them.

Structural Trust Score

High, medium, or low — scored from source authority, freshness, outbound link quality, and content signals. Decide whether to cite, verify, or skip.

Outbound Authority

Scores the quality of every domain the page links to — strong external citations are a trust indicator that can't be faked.

Archive Availability

Checks the Wayback Machine for a snapshot of the page — if the live page disappears, your agent knows a cached copy exists.

Freshness & Integrity

Freshness Detection

Publish dates extracted from meta tags, schema, and headers. No date found? Your agent gets an explicit staleness warning.

Correction Detection

Flags when a page has been revised or corrected after publication — your agent knows whether it's reading the original version or an updated one.

Syndication Detection

Flags when content matches wire copy or near-identical text already seen on other domains — so your agent does not mistake five copies of one story for five independent sources.

Paywall & Truncation Detection

Flags when a page was cut short — paywall, subscription gate, or partial render. Your agent knows when "clean Markdown" is not the whole story.

Content Understanding

TL;DR

The page's own summary, structured and ready to cite. Extracted from the page itself — no LLM paraphrasing.

Key Figures

Prices, percentages, stats — extracted upfront into a structured array. No scanning 3,000 words for the numbers.

Content-Type Classification

News, tutorial, product page, forum, academic paper, and more — classified upfront so your agent can reason about the page the way it is meant to be read.

Reading Time

Estimated minutes to read the full page, computed upfront — your agent knows the depth of the content before it commits.

Language Signals

Hedge-Language Density

Measures how much of the page's language is hedged or uncertain. High hedge density warns your agent that claims may be speculative even from high-authority sources.

Content Density

Flags thin content — pages that are mostly filler wrapped around a small amount of actual information. Even fresh, authoritative pages can be content-poor.

Boilerplate Ratio

Measures how much of the page is nav, footer, and cookie-banner noise versus real content — your agent knows the extraction was clean.

Response — Now includes litmus
{
"markdown": "# Article Title...",
"metadata": { "title": "...", "domain": "techcrunch.com" },
"litmus": {
"source": { "type": "news", "authority": 0.82, "rationale": "news source" },
"freshness": { "published": "2026-08-04", "age": "4 days ago", "stale_warning": null, "modified": "2026-08-06", "has_correction": true, "correction_note": "Contains correction/update marker — page was modified after publication" },
"tldr": "Acme Robotics raises $3.5 billion Series E at $61.5 billion valuation.",
"key_figures": [{ "value": "$3.5 billion", "context": "Series E raise" }],
"structural_trust_score": { "level": "high", "trust_factors": ["High-authority source"] },
"hedge_language": { "density": "low", "markers_found": 3, "per_500_words": 1.2 },
"content_density": { "thin_content": false, "substantive_sentence_ratio": 0.68 },
"syndication": { "detected": false, "note": null },
"paywall": { "detected": false, "note": null },
"content_type": "news_article",
"reading_time": { "minutes": 5 },
"is_archived": { "archive_org": true, "archive_is": false },
"outbound_authority": { "score": 0.64, "top_domains": ["reuters.com", "bloomberg.com"] },
"boilerplate_ratio": { "ratio": 0.12, "confidence": "high" }
}
}

Correction detection ships inside the freshness object — a correction is a page modified after publication, so the signal is scored against its own dates.