Frequently Asked Questions

BiasChecker.ai uses AI to analyse text for potential bias, manipulation, logical flaws, and other issues. It offers multiple analysis types including bias detection, manipulation analysis, scientific and legal assessments, historical parallels, and more.

Think of it as a second pair of eyes that helps you read more critically.

Overview is a combined read of an article, built from the other analyses rather than a fresh read of the text. It gives you a one-sentence verdict on what the piece is doing to its reader, up to three cross-checked takeaways, and a note on what the article does fairly. Every supporting quote is reused from the underlying analyses and validated by our code, never invented.

Because it synthesizes other results, Overview needs the core analyses of the article to exist. If you have already run them, building the overview costs exactly one synthesis run. If not, it offers to run the missing ones for you and states the run count before anything starts. Analyses that are already available are always reused free, and the quick pre-check that suggests which analyses fit an article is free too.

See the methodology page for how the combined verdict is computed.

When you submit text for analysis, it goes through a multi-stage AI pipeline:

1. Content capture: The text is taken directly from what's displayed in your browser — either the whole page or a specific selection you highlight.
2. Translation note: If you've translated the page using your browser or the website's translation feature, the translated text is what gets analysed, not the original language.
3. AI analysis: The text is evaluated for bias, manipulation, and other issues depending on which analyses you select.

The process typically takes 5–20 seconds, but the time varies with the length of the text, the analysis type, the AI model you choose, and how busy the service is at that time of day. During peak periods — or for long articles on slower or premium models — an analysis can occasionally take a few minutes.

For a fuller picture of how analyses run — the principles every analysis follows and what each analysis type looks for — see our methodology page.

Bias analysis examines the article text across 30 bias categories — framing, omission, source imbalance, political and other slants — and surfaces the specific passages that drive each finding.

1. Detection: The AI reads the article and flags biased framing, loaded language, missing perspectives, and one-sided sourcing, citing the exact evidence for each.
2. Scoring: Findings are weighted by severity into an overall signal (none / low / medium / high) so you can see at a glance how slanted the piece is.

Like every other analysis (Reveal Intent, Persuasion, Scientific, Legal, Moral, Historical Parallels, Critique, Omissions, Background, and Roast), bias analysis runs on the original text.

Two different ratings appear on a bias result, and they measure different things:

• The overall Bias Level (none / low / medium / high) measures this article. Each finding contributes points according to its category's severity — a high-severity category (like framing or omission) counts twice a medium one, and an easy-to-spot category counts half — and the totals are tiered so that a single trivial, easy-to-spot indicator still reads as none, one or two findings read as low, a handful as medium, and only a broad pattern of serious categories as high. Heavy spin shows up as several serious categories at once, not as a long tail of minor issues. We deliberately don't use the AI's own numeric scores: they aren't calibrated across models, so the same article could rate differently depending on which model ran it.
• Each indicator's severity badge (low / medium / high) classifies the type of bias found, not its intensity in this particular article. Every category in our bias catalog is rated by its impact on the reader and by how easily an unaided reader can spot it: high-impact biases rate high, and a bias that is easy to notice rates one step lower — a slant you can see through does less damage than one that works invisibly. Because the rating is a property of the bias type, the same category always carries the same badge, whichever AI model produced the analysis.

Findings also show their cited evidence. Where an excerpt is marked verified, we located it verbatim in the article text — quotes the AI paraphrased or that we could not locate are shown but not counted as verified.

So a one-sided press release can rate high overall with several high-severity categories, while a lightly slanted news report might rate low overall yet still list a framing indicator — one serious category on its own signals a lean, not heavy spin.

English is fully supported with all features.

Other languages will work, but with some limitations:

• Analysis quality may be lower than for English content.
• Results are still reported in English, regardless of the input language.

By design, BiasChecker.ai adopts a critical perspective — its job is to look for potential weaknesses, gaps, and issues. This means the results will naturally focus on what could be improved rather than what the content does well.

This doesn't mean the content is bad. Even high-quality, well-researched articles may contain subtle framing choices, missing perspectives, or structural patterns worth thinking about.

The analysis is one perspective to consider, not a final verdict. Always use your own judgment alongside the results.

No. AI-generated analysis may express findings in strong, categorical language (e.g. "this claim is unsupported") even when the reality is more nuanced. This directness is a characteristic of how the AI communicates, not a guarantee of accuracy.

The AI can make mistakes, miss context, or flag things that are perfectly reasonable. It may also miss genuine issues. Results should always be treated as suggestions for further thought, not as established facts.

For more details, see section 2.2 (AI Disclaimer) and 2.5 (Critical Nature of Analysis) in our Terms of Service.

A single AI model can have blind spots and quirks. Consensus is the answer to that: instead of one model, a panel of models from different AI providers each analyses the article independently, and an editor model then merges their findings into one result. The rule is strict: a finding only makes it into the consensus when at least two models independently support it. Anything raised by a single model is dropped, and this is enforced automatically, not left to the AI's judgement.

• What you get: a normal-looking result containing only the findings the panel agrees on, with a note at the bottom naming the exact models the judgement rests on. If the models agree on nothing, an empty result is the honest outcome: the panel found no issues in common.
• Where to find it: pick Consensus from the model dropdown (in its own "Multi-model" group). It's offered on verdict-style analyses such as Bias, Persuasion, Legal, Moral, Scientific, Critique and Omissions; interpretive modes like Intent, Background, Parallels, Rewrite and Roast have no agree/disagree concept, so it doesn't apply there.
• What it costs: you're charged for the models that actually run. The dropdown shows the maximum, but panel members whose results are already cached for the page are re-used free, so a consensus on a previously analysed article is often much cheaper, and its members' individual results become available to everyone afterwards.

If one panel model fails to respond, you still get a consensus from the remaining models, clearly flagged as a partial panel with a suggestion to re-run for full coverage. Consensus results are a strong default when you care about reliability; a single-model run remains the right choice when you want a specific model's take or the fastest, cheapest answer.

The Roast is a purely comedic analysis mode — a warm stand-up bit about the article. It gives you a punchy verdict, a playful retelling, and a few standalone jokes about its most roastable details. Think of it as a friendly, witty companion who finds the funny in the news.

The humour is designed to be warm and good-natured — it targets the writing and framing, never individuals, victims, or people in vulnerable situations. The bar is whether there's genuinely something funny: a dry, well-written piece gets nothing to roast, and tragedies or sensitive human stories (serious illness, grief, disability) are never joked about.

Comedy is subjective, and some users may find the tone too direct. If that's the case, the other analysis modes surface what's actually weak about an article in a straightforward format.

BiasChecker.ai is not a traditional fact-checking service, but several analysis types do evaluate content against established knowledge and frameworks:

• Scientific Assessment checks claims against established scientific consensus and known research — it can flag statements that contradict well-established science, misrepresent study findings, or use pseudoscientific reasoning
• Legal Risk evaluates whether proposals or actions described in the text comply with applicable laws and legal principles
• Moral Lens evaluates content against universal ethical principles such as dignity, honesty, equality, and justice

Other analysis types — such as bias detection and manipulation analysis — focus on identifying patterns, framing choices, and rhetorical techniques rather than verifying specific facts. (The Roast is the odd one out: it's pure comedy, not an analytical check.)

For broader factual verification, we recommend using dedicated fact-checking services alongside our analysis.

No. The analysis is for informational and educational purposes only. It does not constitute legal, medical, scientific, or any other form of professional advice. Always consult qualified professionals for decisions in these areas.

Because the Service is designed to err on the side of caution, it may occasionally flag items that are, in context, perfectly reasonable. This is sometimes called a "false positive."

We are actively working to reduce false positives through continuous prompt engineering and model tuning. Large language models are also becoming significantly more capable over time, so you should expect the accuracy and nuance of our analysis to keep improving.

That said, the goal is to prompt you to think about a particular aspect of the text — not to declare it definitively flawed. If you consider the flagged item and decide it's fine, that's a perfectly valid outcome.

All AI systems have limitations and may reflect biases from their training data. We take this seriously and use several techniques to counteract it:

• Prompt engineering: Our analysis prompts are carefully designed to instruct the AI to focus on the writing and reasoning rather than on the identities or political positions of the people involved.
• Continuous improvement: We regularly review analysis results, refine our prompts, and evaluate newer models. As LLMs become more capable, the quality and fairness of our analysis improves with them.
• Multi-model analysis: You can run analyses using different AI models — Claude, Gemini, Grok, and others — whose training data and methods are fundamentally different. By comparing results from independent models, training-specific biases become much easier to spot. If two models trained on different data disagree, that disagreement itself is a valuable signal. Model selection is available to every signed-in user, on all plans, from the side panel.

Despite these measures, no system is perfectly neutral. This is why we encourage users to treat results as a starting point for critical thinking, not as an authoritative judgment. For more on our approach, see our About page.

We do not store the original text you submit. Only the analysis results are saved.

Saved results are re-used when anyone analyses the same content — so if another user submits the same article, they will see the same results instantly instead of waiting for a fresh analysis. This makes the service faster and more affordable, but it means analysis results are not private to your account.

We do not share your submitted content or analysis results with third parties outside the service. For full details on data handling, please see our Privacy Policy.

Here are a few tips:

• Try multiple analysis types: Different analyses reveal different aspects of the text. The bias analysis and manipulation check each offer unique insights.
• Read the evidence: Each finding includes a quote or reference from the original text. Check whether you agree with the interpretation.
• Use it as a conversation starter: The results are most valuable when they prompt you to think more deeply, not when taken at face value.
• Compare sources: Analyse the same story from different outlets to see how framing and emphasis differ.

It's an estimate, not a fixed allowance. Every analysis is billed by the actual tokens it uses (roughly, the length of the article plus the analysis) multiplied by your chosen model's rate — so a short article on a 1× model costs a fraction of a long article on a 10× model. Because each analysis costs a different amount, we can only project how many you have left.

• When you're getting started, we use a typical cost of about 5,000 tokens per analysis (a mid-length article on a 1× model) to show a ballpark figure.
• Once you've built up a representative history — around 30 analyses, or after you've used about 10% of your allowance, whichever comes first — we switch to your own average. That average already reflects the models and article lengths you actually use, so if you favour premium models the count adjusts down to match.

The same applies to pay-as-you-go credit balances: until you've run about 30 analyses or used roughly 10% of a credit pack, we show a ballpark at the standard 1× rate; after that, the count reflects the models you actually run. The estimate refreshes as your usage evolves, so it gets more accurate the more you use it.

Every analysis is saved against the article and the model that ran it, so re-opening one that already exists is free — it doesn't use an analysis. Running something genuinely new — a different article, a different analysis type, or the same analysis on a different model — still counts as normal.

In the browser extension you can turn on Prefer cached results (Settings → AI Model Preference). With it on, opening or switching an analysis loads an existing cached result for the page instead of running a fresh, paid one — a simple way to make a trial or a credit pack last longer.

• If the model you've selected already has a cached result for the page, that one loads.
• If it doesn't, the extension loads the best result that is cached (most capable model first), rather than nothing — so your default-model choice never hides analyses that other models have already produced.
• Only when nothing is cached for that analysis does it run a fresh one, using the model you selected.

So you don't need to keep changing the model dropdown to browse what already exists — change it only when you specifically want a fresh run on a particular model. Trial users who have used up their allowance keep free access to cached and community results for the rest of the trial period.

And it's not only your own analyses: when someone else has already run an article, that cached result is shared with you too. With Prefer cached results on, simply opening the article you want is usually enough to pick one up — wherever it's published — so you don't need to go looking for it. The extension's Community Analyses page is a handy window into some of what's already out there, but it's a curated, partial list, not everything that has been analysed.

Each analysis tab in the extension's side panel carries a small dot in its corner. It answers one question at a glance: is there anything here for me?

• No dot: this lens has not been run on this page yet, by you or anyone else.
• Grey, blinking: analysing right now. Results usually arrive in 5 to 20 seconds.
• Green: the page was checked and nothing notable was found. You can skip this tab with confidence.
• Yellow: there is something to read: either the lens found issues worth your attention, or it produced its analysis (lenses like Intent, Background, Parallels, Rewrite and Roast always produce content rather than a pass/fail verdict).
• Red: the analysis failed. Open the tab to see why and retry.

Because analyses are shared, dots can appear before you run anything: a yellow dot means results for that lens already exist for this page and open instantly (reading an existing result is free on most plans), and a green dot means at least one AI model already went through the page with that lens and found nothing notable, so you probably don't need to spend a run on it.

The dot always shows the best current knowledge, and your own result wins: once you run a lens yourself, the dot reflects what you saw. Per-model detail lives in the model dropdown, where a ✓ marks each model that already has a cached result for the current lens.

Upgrading takes effect immediately — your new, larger monthly allowance is available as soon as the payment goes through, and your renewal date stays the same.

You only pay the difference, not a full new month. We credit the unused part of your current plan and charge the new plan for the rest of the current billing period, so the amount taken today is prorated — usually small. From your next renewal onward you simply pay the new plan's normal monthly price.

Whatever you've already analysed this month carries over: your bigger allowance applies to your existing usage rather than starting a fresh one on top of it. For example, if you've nearly used up a Lite allowance and upgrade to Pro, you get Pro's larger allowance with what you've already used this month counted against it — leaving the remainder for the rest of the period. The full new-plan allowance refreshes on your normal renewal date.

Moving to a lower tier works the other way around: it takes effect at the end of your current billing period, so you keep the plan you've paid for until then.

We'd love to hear from you. Please visit our Contact page to get in touch.