Our Methodology
Every BiasChecker.ai analysis is an AI-assisted close reading of an article, run under a fixed set of instructions we have refined over thousands of analyses. The instructions are the same whichever AI model you choose — a different model changes who does the reading, not the instructions.
This page introduces the thirteen analysis types — we call each one a lens — and how to read the verdict each one returns. For the exact questions behind every analysis — and the ground rules they all share — see the questions behind every analysis.
We read the page, not the person
Every analysis describes the writing: what a piece is built to make you see, feel and conclude, and how it does it. Each finding is tied to a quote you can check yourself.
We do not claim to know why someone wrote something. Results talk about the article, never the journalist or publisher: “the piece steers you toward…”, not “the author wants to hide…”.
How to read a verdict
Most lenses lead with a verdict — a quick, at-a-glance read of the result. Like every rating on the site it is computed by our code from what the lens found, never asked of the AI model. It comes in three forms; each lens entry below says which form it uses and what its levels mean for that lens.
Banner with a count
Persuasion, Bias Analysis and Omissions lead with one line that states the level in words and counts what was found, for example “Leans clearly: 3 findings” or “Steers the reader: 3 techniques”. The symbol and colour show the level: ✓ green for none, ◇ blue for low, ◐ amber for medium and ✕ red for high.
Concern & Evidence chips
Scientific Assessment and Synthesis lead with two chips:
- Concern — None, Low, Medium or High — how much the lens found worth flagging; each lens entry below says what sets it. Broadly, None means nothing notable, Low one isolated point, Medium a handful, and High a piece dense with them.
- Evidence — Limited, Moderate or Strong — how much verified, quoted support backs those findings.
Verdict headlines
Critique, Legal Risk and Moral Lens lead with one of a few fixed phrases and no count: for these lenses one decisive problem matters more than several background notes, so a count would mislead.
The remaining lenses (Intent Analysis, Background, Historical Parallels, Neutral Rewrite and Roast) carry no verdict at all — they exist to inform, reframe, or entertain, not to flag concerns.
Indicators, not accusations. Every result is an AI reading of the text, not a fact-check or professional advice; see our Terms.
The thirteen analyses
Each analysis type gives the model a different expert role and a different question to answer about the same article. They fall into four families: Slant (how the piece leans and steers), Substance (whether what it argues holds up), Context & Extras (background, historical parallels, a neutral rewrite and a roast), and Synthesis (an analyst's report written from the rest). For a closer look at the exact questions behind each one, see the questions behind every analysis.
Slant— Spot the slant
Intent Analysis
Identifies what the text says versus what it steers readers to believe or do. Intent is treated as a property of the writing: the direction the text pushes. The result names the text's primary purpose and direction, and gives you a quick verification question you can check for yourself in seconds. In detail
Verdict: none; this lens informs rather than flags.
Persuasion
First asks whether the writing pushes you further than its facts support; straight reporting usually doesn't, and then nothing is listed. Where it does, each passage that pushes is named as one of eight persuasion techniques, with the exact quote and how it works on the reader. A passage that does not clearly fit a technique is left out. In detail
Verdict: Banner with a count (see above). A rough measure of how hard the piece works to move you, in four steps: Doesn't steer the reader, Steers lightly, Steers the reader and Steers the reader hard, followed by the number of techniques found. Each technique carries a fixed weight from our catalogue, so the level reflects how serious the techniques are, not just how many. Steers lightly: a minor technique or two. Steers the reader hard: several serious techniques stacked together, often a sign that the conclusion the piece steers you toward isn't the one its own facts (or its headline) actually support.
Bias Analysis
Describes how the text leans, with reference to specific words and structural choices, across our catalogue of bias categories — framing, loaded language, selective facts, source imbalance, political slant and more. Each finding cites the passages that drive it. In detail
Verdict: Banner with a count (see above). A rough measure of how much the framing, rather than the bare facts, shapes the impression you come away with, in four steps: No clear lean, Leans slightly, Leans clearly and Leans heavily, followed by the number of findings. Each finding is weighted by how impactful its bias category is. Leans slightly: a few minor or easy-to-spot leanings. Leans heavily: slant runs through the piece across several high-impact categories (framing, political slant, selective facts), so it reads more like a particular take than neutral reporting. A heavy lean is about emphasis and selection. It does not mean any individual fact is false.
Omissions
The "what's missing" lens: what a well-informed reader would expect to see but the article leaves out, why each gap changes the impression the article leaves, and what kind of source would fill it. Only well-established context that would change your reading counts, so a thorough, balanced article comes back with an empty list. Where the article may have a serious flaw that cannot be stated as fact, the lens may add one or two neutral "questions worth asking" so you can weigh it yourself. Before you see the result, a second model checks each claimed gap against the article and removes any the article does in fact cover. In detail
Verdict: Banner with a count (see above). A rough measure of how complete the picture is. The banner counts the key gaps, missing points that change the impression the article leaves, and the background gaps a fuller piece would add, for example “2 key gaps, 1 background”. Key gaps set the level: one is low, two or three medium, four or more high. At high, treat the article as a partial view and look for the missing context. Background gaps on their own raise it to low at most, and only when there are two or more.
Substance— Check the substance
Critique
The "does it hold up?" lens. It states what the article argues, assesses the goal and the approach, lists the flaws that break or weaken the conclusion, and, when the argument fails, suggests a better approach. When an article reports an open plan or agreement, it judges that decision and says so. In detail
Verdict: Leads with one of holds up, partly holds up, or doesn't hold up as presented. Each flaw is marked as a key flaw that breaks the conclusion or a minor one it survives; only the key flaws set the headline. When the article reports an open plan or agreement, the headline judges that decision instead.
Legal Risk
Assesses whether actions or proposals described in the text raise questions under applicable law, working out the relevant jurisdiction from the text itself. About people and unverified facts it stays conditional: it says what would need checking. In detail
Verdict: Leads with one of no red flags, legal context only, or legal questions raised. Each finding is either a red flag — a specific party's conduct of the kind courts or regulators act on — or background legal context, and any red flag sets the headline. It is not a finding that anyone broke the law, only that, if the article is accurate, these are points a lawyer might want to examine.
Moral Lens
Judges two things separately: how the writing treats its subjects and its readers, and how the actions it describes measure against widely shared moral principles. In detail
Verdict: Leads with a two-part sentence, for example “the reporting is fair; the events it describes raise ethical concerns”, so neutral coverage of grave events is never presented as a flawed article.
Scientific Assessment
Checks the scientific rigor of the text: whether claims are supported by the evidence offered, how methodology and statistics are used, what is settled science and what is genuinely disputed, and where the text claims more than its own sources support. In detail
Verdict: Concern & Evidence chips (see above). A rough measure of how much to trust the science as presented. The level follows the number of rigor problems found. Low: a minor issue such as overstated certainty. High: several rigor problems — unsupported causal claims, misused or cherry-picked evidence — so the scientific claims warrant independent checking before you rely on them.
Context & Extras— Get the context & extras
Background
A neutral briefing for someone landing mid-story: what this topic is, how it developed, and where it stands now. Pure orientation, without taking sides, rather than a critique of the article. Where the public record allows, it adds a "what was promised versus what happened" note: early forecasts or pledges set against how they turned out. In detail
Verdict: none; this lens informs rather than flags.
Historical Parallels
A historian's lens: finds past events and patterns that parallel the situation described — analogies, not a timeline of the topic itself — and explains how each parallel resembles the present case and how it played out, ranked by relevance. When none is close, the result says so above them: “No close historical parallel. These are the nearest.” In detail
Verdict: none; this lens informs rather than flags.
Neutral Rewrite
The article rewritten neutrally and more briefly: the loaded language and persuasion stripped out, the padding cut, and every fact, quote, and attribution kept exactly as the original had them. It only removes — it never adds a fact, a figure, or context that wasn’t in the article, so it cannot restore perspectives the original left out. Read it as a shorter, spin-free version and check it against the original before quoting. In detail
Verdict: none; this lens informs rather than flags.
Roast
A warm-hearted comedian doing a stand-up bit about the article — a punchy tagline, a playful retelling, and a few standalone jokes about its most roastable details. The bar is whether it’s genuinely funny, not whether there’s a flaw: a dry, clean piece gets nothing to roast, and tragedies or sensitive human stories are never joked about. In detail
Verdict: none; this lens informs rather than flags.
Synthesis— Then let it all come together
Synthesis
An analyst's report on the article, written by combining the other analyses' stored results — never a fresh, independent read of the text. It always rests on the four core slant lenses, plus any further lenses you add on the setup card; analyses you already have are reused, and nothing runs until you confirm. The report leads with a one-sentence "what this article is doing", connects the findings into one story about how the piece works on its reader, credits what checks out, and closes with a note on how to read it. Any passage our defamation check rejects is left out, and the report says how many were. How it works together with Consensus is covered under Synthesis below. In detail
Verdict: Concern & Evidence chips (see above). Taken from the inputs: the highest Concern any of them reached, except that High needs two inputs at High — so one alarmed lens raises the report to at most Medium, while its own finding stays on its own tab. Evidence counts the quotes carried over from the inputs.
Synthesis — one report, a panel of analyses
Every other analysis reads the article. Synthesis reads the analyses this article already has, and never re-reads the article to form opinions of its own. In detail
Synthesis and Consensus do different things, and they can be combined. Consensus takes one analysis and runs it across several models, reporting where they agree. Synthesis takes one model and runs it across several analyses, reporting how they fit together. Run the lenses you care about as Consensus first and the two combine: Synthesis uses those panel results whenever the model you chose for the synthesis has not run that analysis itself, so the report rests on what several models agreed.
Consensus — one analysis, a panel of models
Any single AI model has blind spots. For Bias, Persuasion, Legal Risk, Moral Lens and Scientific Assessment you can run Consensus instead: several models from different makers each analyse the article independently, and a separate model merges their findings into one result, under the same instructions as a single-model run. In detail
- One seat per maker. Models are grouped by the company that built them, and the panel seats one model per maker, from three makers or more. Two models from the same maker share training data and house style, so their agreement is not a second opinion.
- Agreed findings first. A finding enters the consensus only when at least two models report it independently; what a single model found still appears, in a separate list headed Raised by one model.
Where the panel agrees is the strongest read an analysis can give. Pricing and when to choose Consensus are on the models page and in the FAQ.
Publisher content & community analyses
When you ask for an analysis, the text (read from the page in your browser, or pasted on our site) is sent to us to analyse. For a YouTube or TikTok video the extension reads the captions, not the page around the player.
- Shared results show our analysis, not the article. Other users see our commentary plus short markers that find the quoted passages on the live page, never the article text or a video's transcript. Excerpts shown with findings are short, attributed and linked to the source.
- Only listed outlets reach the community feed. The feed is visible only to signed-in users, and only for outlets on a hand-maintained list. An outlet that opts out of text-and-data mining (
tdmrep.json, ai.txt or anoaidirective) stays off it. Videos come only from those outlets' own YouTube channels. - Disputes. Readers can rate any shared analysis, and one that enough readers flag as inaccurate is hidden automatically. Publishers can ask us to review or remove an analysis of their content via the contact page.