Frametra

Frametra reads the architecture of a news story, not its conclusions.

Most media bias checkers tell you whether a source is "credible." Frametra shows you why, by measuring the structural choices that shape any piece of writing: how claims are attributed, how much evidence supports them, and how the language itself is built. It's an AI-powered news analysis extension for anyone who wants a clearer-eyed way to read the news, check a source before quoting it, screen coverage before a client sees it, or audit their own writing before it goes out.

Click Analyze on any article and get a real-time Structural Integrity Score in seconds. No account required. No political labels. No black box.

The methodology

Frametra's source-diversity scoring is grounded in the JeRI framework, developed by Adamson and Malik at Toronto Metropolitan University. JeRI evaluates who gets to speak in a story, whose perspective is left out, and how claims are supported or left to stand alone.

Frametra is not a fact-checker and does not issue partisan verdicts. It will not tell you a story is left-leaning, right-leaning, true, or false — it tells you how the story is constructed, and gives you the structural evidence to judge that for yourself. A story can be structurally sound and still wrong about facts, and a poorly sourced story can still turn out to be accurate. Frametra measures construction, not truth.

Before scoring, Frametra also classifies the article's genre — News Report, Opinion/Op-Ed, Analysis/Explainer, Feature, Press Release, or Other — and scores it against that genre's own structural norms, rather than holding an Op-Ed and a wire report to an identical, genre-blind bar.

Six forensic signals, every article Claim Pressure — density of assertive claims relative to supporting evidence and article length Source Attribution — named sources, direct quotes, and hyperlinked citations per claim Editorial Integrity — loaded language and passive-voice framing versus neutral reportage; the signal most people mean by "bias," measured structurally instead of politically Epistemic Hedging — whether uncertainty is acknowledged and calibrated, or asserted with false confidence Evidence Signals — numeric references, data points, and documentary grounding behind claims Passive Voice Ratio — whether responsibility for actions is stated clearly or obscured

How it works Install the extension. It sits quietly in your browser until you need it. Visit any news article and click Analyze. The free heuristic engine runs entirely on your device, so no article text leaves your browser at this tier. Get an instant integrity score and a plain-language breakdown by signal, with the exact evidence phrases from the article highlighted directly in each finding. On paid tiers, run a deeper AI-assisted Deep Analysis pass for richer findings, source-level detail, exportable reports, and your heuristic and AI-verified scores shown side by side, instead of one number silently overwriting the other.

What's in the panel

Source Library tracks every named source you encounter across every article you analyze, organized by JeRI source category, flagging when a source has only ever appeared in one outlet's coverage across several tracked pieces. Framing Balance gives a plain-language read on which perspectives are present in a story and which are missing — descriptive, not a left-right rating. Narrative Timeline shows how a story's framing shifts across its own coverage. Annotated Article export produces a downloadable PDF of the article's own text with the exact evidence phrases behind each finding highlighted at their real location in the source, color-coded by signal, rather than listed separately. Translate to English turns any foreign-language article into a clean, readable English PDF — if the article's already in English, Frametra tells you instead of generating anything. Recently Analyzed lets you jump back to any article you've already scored. Your Plan compares what your current tier includes against what upgrading unlocks.

Who uses Frametra

Journalists and Writers audit a source before quoting them, or their own draft before filing it — the Draft Scanner detects Google Docs, WordPress, Substack, Ghost, Medium, and Notion, flagging thin attribution before an editor has to.

Journalism Educators give students a hands-on, citable framework instead of an abstract lecture on media bias. Certificates can be labeled with a student name or class code for classroom submission, no roster setup required.

Researchers and Fact-Checkers apply one consistent structural methodology across many articles instead of a manual read-through of each one.

Legal Professionals document the structural pattern of media coverage relevant to a case, with a labeled case reference field and a built-in not-legal-advice disclaimer.

PR & Crisis Communications Professionals screen releases and client coverage on a fixed monthly retainer scaled to review volume, not a case-by-case negotiation.

Everyday Readers get the same six-signal engine, on every article, for free — a media literacy tool that runs quietly in the background of normal reading, not a separate chore.

Choose your plan

Free, no account required. The complete six-signal heuristic engine, unlimited use, no sign-up, no credit card. Not a stripped-down trial — the same structural engine, with paid findings shown as a preview.

Deep Analysis Pro — $19/month or $149/year. AI-assisted deep analysis, Draft Scanner, emotive tone mapping down to the phrase level, paragraph-level audit flags, the Framing Balance indicator, the persistent Source Library, Narrative Timeline, Domain Reliability Signals, full forensic report export, an Annotated Article export, English translation of foreign-language articles, and a downloadable Structural Certificate.

Education Pro. The full Deep Analysis Pro engine at a standing discount via a group code for a classroom or institution — no seat limit, no per-student setup. Details at frametra.com and frametra.ca.

Counsel Pro. The full forensic suite applied to litigation-relevant coverage, with a labeled case reference field, a preparer field, and a built-in disclaimer stating plainly this is analysis to support counsel's own judgment, not legal advice or expert testimony.

PR & Crisis Communications Retainers. Fixed, published monthly tiers scaled to review volume, with a flat published overage rate and no case-by-case negotiation. A $99 one-off Pre-Publication Review is also available for firms not ready to commit monthly. Full breakdown at frametra.com.

Privacy

Free-tier analysis runs entirely locally in your browser. No article content or browsing history leaves your device at this tier, and nothing is logged or sold, regardless of tier. If you upgrade to a paid tier, the text of the article you choose to analyze is sent to Anthropic's API for AI-assisted review. This is disclosed here and in our privacy policy in full, and that content is never used to train models or shared with advertisers. Translating an article works the same way — the text goes to Anthropic's API to produce the translation, under the same disclosure.

Research and resources

Frametra also maintains a research catalog of source-diversity audits, structural methodology guides, and curriculum packs — including JeRI Framework Applied: Canadian Media, a Media Literacy Curriculum Pack, and How Disinformation Is Built. Available at frametra.com.

FAQ

Is Frametra really free? Yes — the free tier is the full six-signal heuristic engine, unlimited use, no account and no credit card required.

Does my article text leave my browser? Not on the free tier. On a paid tier, only the article you choose to analyze is sent to Anthropic's API for AI-assisted review or translation, disclosed in full in our privacy policy.

Is there an education discount? Yes — institutions and classrooms get Deep Analysis Pro at a standing discount through a group code issued to your program, no per-student setup required. Contact education@frametra.com, or Canadian institutions can visit frametra.ca.

Can I cancel anytime? Yes, from your account dashboard, with no cancellation fees — access continues until the end of your current billing period. Payments are processed securely through Stripe. We offer a 7-day full refund on first-time subscriptions.

Does Frametra tell me if a story is biased? It tells you how a story is structurally built, not whether it's true or which side it favors. Frametra measures attribution, evidence, hedging, and framing, and leaves the judgment about accuracy or fairness to you.

About Frametra

Frametra Software Inc. is an independent Canadian company based in London, Ontario, applying the JeRI structural journalism framework from Toronto Metropolitan University in an everyday browser tool. We're small, and still building. If a score looks wrong or something's confusing, we want to hear about it directly: sales@frametra.com.