2 items
Evaluate source authority, evidence strength, and communication quality for YouTube, podcasts, and articles. Get informed on how reliable the knowledge is on YouTube podcasts like The Diary Of A CEO, Huberman Lab, and Lex Fridman — Evidence Lens helps you look at information through the lens of evidence. Not "is this true?" — that's not a question a browser extension should answer for you. Instead, Evidence Lens asks the questions that actually determine how much confidence to place in something before you trust it: • Is the source a credible authority on this specific topic? • Is the supporting evidence strong? • Was that evidence communicated faithfully — or oversold? • Can you independently verify it yourself? While you watch YouTube or read Medium, Evidence Lens shows a Knowledge Signal next to the content: ▮▮▮ Worth Watching ▮▮☐ Watch Critically ▮☐☐ Verify Before Trusting Click it for the "why" — source credibility, evidence strength, and communication integrity, broken down separately. For interviews and podcasts, Evidence Lens evaluates the guest, the host, and the content separately, since a weak host lets bad claims go unchallenged even when everything else looks credible. WHAT IT CHECKS • Source: does this person's expertise actually match this topic — and are their credentials verified through live web search, or only self-reported? • Facilitator: does the host/interviewer challenge claims and ask for evidence, or just let anything pass? • Content: are the load-bearing claims consistent with established knowledge, or just asserted with confidence? A free surface-level signal appears automatically on every video. An optional detailed report — which verifies the guest/host's credentials through live web search — is available on request. Evidence Lens flags (without penalizing on their own) promotional framing, one-sided claims, and sensational language — these only count against a signal when they're paired with weak or absent evidence. A strong, well-supported recommendation isn't bias; an unsupported one dressed up with confidence is what this catches. REQUIRES YOUR OWN ANTHROPIC API KEY Evidence Lens calls Anthropic's Claude API directly from your browser using an API key you provide in Settings. Your key and cached scores stay in your browser's local storage — nothing is sent to us, because there is no "us" in the data path. See the privacy policy for exactly what leaves your browser and where it goes. Currently supports YouTube and Medium. News sites are intentionally out of scope — Evidence Lens is built for explainers, tutorials, interviews, and analysis, not contested current-events coverage.
Jul 20, 2026
rating_count is the Chrome Web Store ratings count, not a written-review count.
Media assets
Screenshots and videos on the listing.
Has promo video
Whether the listing includes at least one video.
Languages
Declared language locales.
Developer website
Listing exposes a developer website URL.
Contact email
Listing exposes a contact email.
Keyword in name
Case-insensitive substring match in the name.
Keyword in description
Case-insensitive substring match in the description.
Keyword occurrences in description
Count of case-insensitive occurrences in the description.
Category user-count percentile
Share of same-category extensions with fewer users (null if unknown).
These are transparent listing completeness / keyword signals, not a prediction of Chrome Web Store search ranking.