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.

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 entire process typically takes 5–20 seconds depending on the length of the text and the complexity of analysis.

Bias analysis is the only analysis that uses anonymised text. It uses a unique dual-pass approach to detect identity-linked bias:

1. Entity extraction: Named entities (people, organisations, places) are identified in the text.
2. Anonymisation: Entities are replaced with neutral placeholders to create an anonymised version of the text.
3. Dual-pass analysis: The AI analyses both the original and anonymised versions independently. This helps detect whether the AI's own training biases are influencing the results based on who is mentioned.
4. Reconciliation: The two sets of results are compared and merged, flagging any identity-linked discrepancies.

This approach helps separate bias in the text itself from bias that might come from the AI's knowledge about the people or organisations mentioned.

All other analyses (Reveal Intent, Manipulation, Scientific, Legal, Moral, Historical Parallels, Critical Analysis, and Critical Roast) use the original text, as they need real-world context to work properly.

English is fully supported with all features, including de-contextualisation (anonymisation) for bias analysis.

Other languages will work, but with some limitations:

• Analysis quality may be lower than for English content.
• De-contextualisation is not applied — bias analysis runs on the original text only.
• 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.

The Critical Roast is a lighthearted analysis mode that uses playful humour and rhetorical questions to highlight potential issues in the text. Think of it as a friendly, witty companion pointing out things you might want to think twice about.

The humour is designed to be warm and good-natured — it targets the writing and reasoning, never individuals, victims, or people in vulnerable situations. If the text is well-written and sound, the roast will say so.

Comedy is subjective, and some users may find the tone too direct. If that's the case, the other analysis modes provide the same insights in a more 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 Assessment evaluates whether proposals or actions described in the text comply with applicable laws and legal principles
• Moral Assessment evaluates content against universal ethical principles such as dignity, honesty, equality, and justice

Other analysis types — such as bias detection, manipulation analysis, and the Critical Roast — focus on identifying patterns, framing choices, and rhetorical techniques rather than verifying specific facts.

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:

• Anonymisation & dual-pass analysis: For the full bias analysis, we first extract named entities (people, organisations, places) from the text and replace them with neutral placeholders. We then run the analysis twice — once on the original text and once on the anonymised version. By comparing the two results, we can detect when the AI's opinion changes based on who is mentioned rather than what is said. A difference between the two passes does not always mean the model is biased — there is inherent randomness in how AI generates responses, so occasional variation is normal. However, if the same pattern appears consistently across multiple analyses, it is a stronger indicator of a genuine model bias.
• Reconciliation: The two analysis passes are reconciled into a single result that flags any discrepancies, giving you transparency into where the AI's own biases may have influenced the output.
• 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, identity-linked and 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 subscribers 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.

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