See the structure
behind every argument.
The Whetstone reads any text as an argument: what's claimed, what evidence is offered, where the logic breaks down, and the strongest opposing case the writer didn't engage. Not a verdict on who's right. A structural view of how the argument works.
The experts who got us here are now telling us not to trust our own eyes. At what point do reasonable people simply stop listening?
Ad Hominem
Attacks the messenger's standing rather than engaging the claim: "the experts are compromised, therefore wrong" doesn't follow.
26
patterns
11
lenses
200M+
papers
How it works
Paste an argument
An op-ed, a thread, a draft, a transcript, or a URL. No account needed to start.
Eleven lenses run
Structure, fallacies, loaded language, hidden assumptions, key terms, testability and more, all in parallel.
See the structure
A structured report: verbatim quotes, severities, and where each finding sits in the argument.
What the engine analyses
Eleven lenses, each grounded in a real tradition of logic and argument analysis: from Toulmin's argument model to key-term, referential, and testability scrutiny. Six of the headline outputs:
Argument structure
Toulmin decomposition: claim, grounds, warrant, and the weakest link. The skeleton of the argument, stripped of rhetoric.
26 reasoning patterns
Post Hoc to Motte-and-Bailey, Selection Bias to Genetic Fallacy, each with the verbatim quote that exemplifies it and a severity.
Counterarguments
The two or three strongest objections a thoughtful opponent would deploy, each steelmanned, each with its own Toulmin structure.
Citation audit
Every cited URL is fetched and checked: does the source actually support the claim it is cited for?
Frameworks made visible
The ethical, epistemic, and political framework the argument operates within, surfaced so you can defend or replace it.
Evidence-weighted likelihood
For empirical claims, we search 200M+ academic papers and synthesise where the scientific consensus actually sits.
What it won't do
It won't adjudicate claims.
The tool analyses argument structure, not the factual accuracy of specific assertions, though the citation and evidence lenses help.
It's not a political moderator.
The same engine runs on a climate-policy argument and its counter. The frame is neutral; the conclusions you draw remain yours.
It's not a writing improver.
It audits but does not rewrite. Preserving your voice is deliberate. Fixing flagged issues stays with you.
It is not always right.
Findings flag structure, not verdicts. Treat them as prompts to look more carefully; calibration improves with feedback.
Three ways to use it
Reader · free
Audit any argument
Paste text or a URL. The full lens suite minus the Studio-tier engines. No account required.
Open the Reader →
Studio · from A$33/mo
Stress-test your writing
Full suite, counterarguments, citation audit, evidence-weighted likelihood, revision tracking, inline highlights.
Open Studio →
Chrome extension
Audit as you read
Analyse any argument inline while reading on the web. Highlights overlay the page itself. Coming to the Web Store.
Coming soon
Open and inspectable
Every prompt, schema, and analytical framework is in the public repository. A tool that shapes how people read arguments should itself be transparent: if a finding seems off, you can read the prompt that produced it.