Frametra

Structural journalism forensics. Analyze media integrity, detect claim pressure, and generate certified integrity reports.

Frametra reads the architecture of a news story, not its conclusions. Most media bias checkers and fact-checking extensions tell you whether a source is "credible" or slap a political label on a story and call it done. Frametra is a structural journalism analysis extension that shows you why, by measuring the actual structural choices that shape any piece of writing: how claims are attributed, how much evidence supports them, how language signals certainty or hedging, and how the piece is framed relative to its own genre. It's an AI-powered news analysis and media literacy tool 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 — the same rigor a fact-checker or editor would apply, made repeatable and consistent across every article. 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. This distinction matters: 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. GENRE-AWARE SCORING Before scoring, Frametra classifies the article's genre — News Report, Opinion/Op-Ed, Analysis/Explainer, Feature, Press Release, or Other — and scores it against the structural norms of that genre. Assertive, first-person argumentation is expected and appropriate in an Opinion piece; the identical language in a News Report presenting itself as neutral fact-reporting gets flagged as a genuine structural integrity issue. This is what separates Frametra from a generic bias checker: it doesn't hold an Op-Ed and a wire report to the same genre-blind bar, because that isn't how journalism actually works. SIX FORENSIC SIGNALS, EVERY ARTICLE Claim Pressure — How much of the text pushes a conclusion versus lets evidence speak for itself. Flags hedged assertions and unverified claim density relative to article length. Source Attribution — Named sources, direct quotes, and hyperlinked citations per claim. Detects when a story leans on unnamed or unverifiable sourcing, and credits sources properly when a claim links directly to its origin. Editorial Integrity — Loaded language and passive-voice framing versus neutral, direct reportage. This is the signal most people mean when they say "bias," measured structurally instead of politically. Epistemic Hedging — Whether uncertainty in the story is acknowledged and calibrated, or asserted with false confidence. Appropriate hedging on unconfirmed details is a sign of careful reporting, not weakness. Evidence Signals — Numeric references, data points, and documentary grounding behind the claims being made. Passive Voice Ratio — Whether responsibility for actions and claims is stated clearly or obscured through passive construction. HOW IT WORKS Install the extension. It sits quietly in your browser until you need it — available for Chrome, Edge, and Firefox. 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 — so you can see precisely what drove the score instead of taking it on faith. On paid tiers, run a deeper AI-assisted Deep Analysis pass for richer findings, source-level detail, and exportable reports — and see your heuristic score and AI-verified score side by side, so the two methods' agreement (or disagreement) is visible instead of one number silently overwriting the other. WHAT'S IN THE PANEL Beyond the score itself, Frametra tracks patterns across everything you read: Source Library. On paid tiers, every named source you encounter gets tracked automatically across every article you analyze, organized by JeRI source category. See at a glance when a source has only ever appeared in one outlet's coverage across 3+ tracked pieces, or when the same person gets classified differently from one article to the next. Sources can be renamed or merged by hand when two mentions of the same person don't match exactly, so the library stays clean over time. Framing Balance. Available on all paid tiers, a plain-language read on which perspectives or stakeholders are present in a story's framing and which are missing. It is deliberately descriptive, not a left-right rating. Narrative Timeline. On paid tiers, a structured view of how a story's framing shifts across its own coverage, plus comparative gaps against related reporting. Recently Analyzed. Jump back to any article you've already scored without re-running the analysis, whether it's still open in another tab or you've since closed it. Your Plan. A built-in comparison of exactly what your current tier includes and what upgrading unlocks, plus a running count of how much you've actually used the tool. WHO USES FRAMETRA Journalists and Writers. Run a structural check on a source before you quote them, or on your own draft before you file it. Frametra's Draft Scanner flags thin attribution or claim-heavy paragraphs before you hit publish, not after an editor catches it. Journalism Educators. Give students a hands-on, citable framework instead of an abstract lecture on media bias. Students can run the same analysis on two outlets covering the same event and articulate, in structural terms, exactly where and how the coverage diverges. The Draft Scanner doubles as a self-editing tool for student writing assignments, and certificates and reports can be labeled with a student name or class code for easy classroom submission — no accounts or roster setup required. Researchers and Fact-Checkers. Apply a consistent, repeatable structural methodology across many articles instead of a manual read-through of each one. The Source Library builds a persistent, cross-article picture of which sources and outlets recur, and where genuine source diversity is present or absent, automatically in the background as you work. Legal Professionals. Document the structural pattern of media coverage relevant to a case, defamation review, or public-perception question. Counsel Pro output includes a clearly labeled case reference field and an explicit not-legal-advice disclaimer built into every document, formatted to support counsel's own review rather than to stand in for it. PR & Crisis Communications Professionals. Screen a release or a client's coverage before it goes further, on a fixed monthly retainer scaled to your review volume — not a case-by-case negotiation. Structural review of how coverage is actually built, before something ends up in front of a client or the press. Everyday Readers. You don't need a professional use case to want a clearer-eyed way to read the news. The free tier gives you the same six-signal engine, on every article, for as long as you use it. Think of it as a media literacy tool that works quietly in the background of your 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. This is not a stripped-down trial — it's the same structural engine running entirely on your device, with paid findings visible as a preview so you know what you'd be unlocking. Deep Analysis Pro — $19/month or $149/year. AI-assisted deep analysis on every signal, the Draft Scanner, emotive tone mapping down to the phrase level, paragraph-level audit flags, the Framing Balance indicator, the persistent Source Library, the Narrative Timeline, Domain Reliability Signals, full forensic report export, and a downloadable Structural Certificate suitable for editorial review or academic submission. Education Pro. The full Deep Analysis Pro engine at a standing discount, distributed as a group code for a classroom or institution — no seat limit, no per-student setup. Built for journalism programs and media studies departments; details at frametra.com and frametra.ca. Counsel Pro. The full forensic suite applied to litigation-relevant coverage, with a dedicated document format: a labeled case reference field, a preparer field, and a built-in disclaimer stating plainly that this is analysis to support counsel's own judgment, not legal advice or expert testimony. PR & Crisis Communications Retainers. Fixed, published monthly tiers for agencies with recurring release volume — Pre-Release Screens with 24-hour turnaround, scaled from a handful of reviews a month up to a full client roster, 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 tier 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. RESEARCH AND RESOURCES Frametra also maintains a research catalog covering source-diversity audits, structural methodology guides, and outlet-level media analysis — including JeRI Framework Applied: Canadian Media for researchers, a Media Literacy Curriculum Pack for educators, and How Disinformation Is Built for journalists and investigators. Available at frametra.com. FREQUENTLY ASKED QUESTIONS Is Frametra really free? Yes. The free tier is the full six-signal heuristic engine, unlimited use, no account and no credit card required. Paid tiers add AI-assisted deep analysis and the features described above. Does my article text leave my browser? Not on the free tier. Free-tier analysis runs entirely on your device. On a paid tier, the text of the article you choose to analyze is sent to Anthropic's API for AI-assisted review, disclosed in full in our privacy policy. Is there an education discount? Yes. Institutions and classrooms can get Deep Analysis Pro at a standing discount through a group code issued to your program — no per-student setup or roster required. Contact education@frametra.com, or Canadian institutions can visit frametra.ca directly. Can I cancel anytime? Yes. Cancel from your account dashboard at any time, with no cancellation fees. Your access continues until the end of your current billing period. Monthly plans renew every 30 days, annual plans renew once per year, and 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. Does Frametra work on mobile or other browsers? Frametra is available for Chrome, Edge, and Firefox as a browser extension. There is no standalone mobile app at this time. 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. Notes on what changed from the previous draft (not for the listing itself) Every reference to Writer Pro and Investigator Pro as separate purchasable tiers has been removed — those merged into Deep Analysis Pro and no longer exist as distinct products. Feature descriptions that said "On Investigator Pro" or "from Writer Pro up" now read "on all paid tiers." Education Pro section corrected to match actual mechanics (institution group code, no seat cap, standing discount) instead of the old "50% off Writer Pro via email" framing, which was specific to a tier that no longer exists. Added a new Genre-Aware Scoring section — a real, current differentiator that wasn't mentioned in the previous draft at all. Added the heuristic-vs-AI-verified score comparison feature (shipped this session) to the "How It Works" section. Added PR & Crisis Communications Professionals as a named audience, and added the PR & Crisis Communications Retainers tier to the plan list — this is now a flagship offering on frametra.com and wasn't represented here at all. Added specific info-pack titles (JeRI Framework Applied: Canadian Media, Media Literacy Curriculum Pack, How Disinformation Is Built) to the Research and Resources section for search-term coverage, matching the titles and keyword framing already live on store.frametra.com. Left the refund/cancellation language exactly as-is — verified it matches your site's own established wording (account dashboard, 7-day refund, Stripe) exactly, not something specific to this listing. Did not include exact retainer tier dollar amounts here (kept it to "fixed monthly tiers... full breakdown at frametra.com") since Chrome listings are slower to update than the site if pricing changes — figured that trade-off was worth flagging rather than deciding silently either way.