Any tool can hand an agent the text of a page. The question that decides whether the answer is any good — should this be trusted, cited, or dropped — is the one nobody was answering.
"Reading it yourself" means handing the raw page to a model and asking what it thinks. It is the honest comparison, not a straw man — and it loses on repeatability, not intelligence.
| For the same URL | Plain extraction | A model reads it | Litmus |
|---|---|---|---|
| Clean Markdown | Yes | Yes | Yes |
| Sees JavaScript-rendered content | Sometimes | Depends | Yes |
| Source type and authority | — | Sometimes | Yes |
| Named author or anonymous | — | Sometimes | Yes |
| Freshness and staleness warning | — | Sometimes | Yes |
| Paywall flagged, not silently truncated | — | Sometimes | Yes |
| Error page / captcha / JS shell detected | — | Sometimes | Yes |
| Syndicated copy detected | — | Rarely | Yes |
| Citations and reference density | — | Sometimes | Yes |
| Thin content and boilerplate ratio | — | Rarely | Yes |
| Same input returns the same output | Yes | No | Yes |
| Auditable in your own logs | — | No | Yes |
| Cost per call | Plan-based | Model tokens | $0.005 |
Not a criticism of extraction tools — they were built to do a different job. But the gap is real and it is where agents fail.
A byline is markup, not text. Strip the page to Markdown and "By Jane Chen, Health Correspondent" either disappears or arrives as a stray line nobody parses.
Publish dates live in metadata, JSON-LD and headers far more often than in the body. The text of a 2019 page and a 2026 page look the same.
A paywall teaser, a soft 404 and a captcha all produce text and a 200. Extraction has no opinion about whether that text is the article.
A model can absolutely form an opinion about a page. The problem is what happens on the second run.
Litmus is not a smarter reader. It is a repeatable one — which is what you need before an agent acts on the answer.
A trust product that overstates itself is worthless, so here are the limits, stated plainly.
If a page is gated, you get paywall.detected: true and a note — not the
article. Bypassing a gate is not the product.
source.authority is a score from observable signals about the domain and
page, not a guarantee of correctness. A high score means "worth reading", not "true".
When a signal cannot be determined it comes back null or "unknown". We would rather hand you a gap than a confident fabrication.
No account, no key, no plan. Send a URL and read the verdict.