How I verify legal claims

How this site is produced

The content is produced in a legal workflow with agentic AI. I work in Claude Code with my own rule set and a library of legislation held on disk. The rules match this methodology and are machine-enforced.

The material comes from my own attempts, notes, ideas and collected papers, including other authors’ thinking. Some of it came out of work on a specific matter, some as a note in the margin of other work, some is read and thought through after someone else. Where the origin of an idea can be traced, I name it.

• Every specific citation of a section or article is checked word for word against the wording in the library. The library holds texts from the Czech Collection of Laws and from the EU Publications Office database.
• Text that interprets a provision is read article by article next to its wording. The check looks for four typical failure patterns: a rule imported from another instrument, a dropped word that changes how binding a rule is, a reference to a thematically adjacent place instead of the normative one, and a case-law summary written from the facts rather than from the ruling.
• Checks run before publication compare the library against the sources and report mismatches. Anything that fails them is not published.

I also go over the content myself on an ongoing basis, adding to it and updating it for new case law, practice and legislative changes. Every change visible on the site is logged with its date in the list of changes.

Sources

I take the wording of statutes from primary sources: the Collection of Laws (Sbírka zákonů) for Czech law, and the Official Journal and EUR-Lex for EU law.

Secondary sources, such as commentaries, scholarly articles, legal portals, or case-law digests, I use mainly as a guide. They help me find the connections, but they do not replace the text of the statute itself.

For my own work I also check citations against a local legal database before they appear in the output.

The three layers of a claim

In legal analysis I keep three things apart:

• Verified law The verbatim text of a provision in force, with a citation you can check against the primary source.
• Interpretation My inference, conclusion, or working opinion. It may be useful, but it is not the text of the law, so I do not label it as such.
• Missing facts Facts of the specific matter that I do not know and that could change the outcome. Rather than guess, I state them as questions or caveats.

The same logic runs through the prompt builder. Two notes go into it in more detail: Working with a statute and Why AI hallucinates on Czech law.

Citing sections

I never cite a specific section from memory alone. First I verify its current wording in the source, and only then do I work with it.

If I have no way to verify a provision, I say so plainly. I do not present the section number or its content as certain until it has been checked.

Effective dates and amendments

Statutes change. The same section can read differently in different periods, and older versions often keep circulating in articles, databases, and the output of language models.

So for legal claims I track not only the number of the provision but also the wording in force at the relevant date. Where it matters, I state the position as of a specific day.

Case law

Links to court decisions point to primary sources where possible, for example Curia, HUDOC, NALUS, or the websites of the Nejvyšší soud (Supreme Court) and the Nejvyšší správní soud (Supreme Administrative Court).

The annotations of decisions are my summaries. They are not a substitute for the full reasoning. Case law supports an interpretation, but before you rely on a decision in a specific matter you need to read it in full.

Revisions

I update the content as I go. Statute cards, research notes, and the course all carry a revision date, so you can see what state they refer to.

When a working hypothesis turns out to be wrong, I do not erase it without a trace. I mark it as disproven, so it is clear what changed and why.

For legislative processes that are not yet finished, I put the caveat directly in the text.

What this site is not

This site does not provide legal services, and its content is not legal advice for a specific case. It is research and educational material that shows the sources and the verification process.

Before you decide anything in your own matter, always check the wording in the source or consult a lawyer. Responsibility for using the information rests with the reader.

The research map shows how the individual working hypotheses come about.