What it can never do.
This is the page careful lawyers tend to like most, because these limits are built, not promised.
The system can read, research, draft, and review. It cannot act in the world on its own.
It never signs anything.
Sign-off belongs to the lead lawyer and cannot be delegated away, even by configuration.3
- 3
You sign off in your own words, from your own address. How sign-off is secured: Security, note 15.
It never guesses.
When a fact cannot be traced to a source document, it halts and flags instead of filling the gap with something plausible.6
When our software can’t check a citation, the email says so, and it is never called verified.7
- 6
Every entry in a court form is traceable to its source document. Anything the file couldn’t fill is listed in the email, and the team never files a guess.
- 7
Every case we cite is checked by our software against the public case-law record. CanLII confirms the case exists and is named correctly, and every quote is checked against the full published judgment to make sure it’s really there. Ask for a verification pass and our review step also reads the paragraph we rely on against what we say it means.
We try to make it cut corners. It has to refuse.
The system runs against a standing set of adversarial integrity scenarios covering the failure modes that matter in law.8 It has to refuse or honestly flag every one, and the set is re-run before changes go live: a standing integrity gate, where every exception is logged and approved by a named person.
The structural limits above are not part of that gate: sending, filing, and signing have no exception path at all.9
On a legal product, the limits are the trust story.
A tool that confidently guesses is dangerous in law. We would rather it hand something back and say it is not sure.
How a firm’s data is handled: Security
Security questions, or something to report: support@caseclarity.ai
There is no contact form. We are a team you email.
Email hello@caseclarity.ai