Compiled by Citation Safe (Digital Empire Holdings LLC) from the court’s published sanction order (decided September 9, 2026). Quotes and case details come from the order itself — check the primary source before relying on them.

Sanction teardown · KB Alberta, Canada · 2026-09-09

Kostic v Scott Venturo Rudakoff LLP

What happened

In KB Alberta, Canada, a filing relied on an unnamed/unconfirmed AI tool to help draft legal argument. The court identified the following problems with the citations in that filing:

Fabricated (Case Law)

The plaintiff cited a nonexistent case for the proposition that security for costs cannot be sought while claims remain unresolved. The court found no case named Fitzgerald v The Co-operators General Insurance Company and noted that 2014 ABCA 106 was actually R v TLG, an unrelated criminal case.
Fabricated (Case Law)

The plaintiff cited a nonexistent case for the proposition that security for costs cannot be sought while claims remain unresolved. The court found no case named Glenmore v Western Canadian Properties and noted that 2019 ABCA 253 was actually R v Hans, an unrelated criminal case.
Fabricated (Case Law)

The plaintiff cited a nonexistent case for the proposition that security for costs cannot be sought while claims remain unresolved. The court found no case named Renaud v The Mutual Fire Insurance Co of British Columbia and noted that 2002 BCCA 378 was actually Sindhar (Guardian of) v Brar, an unrelated personal-injury settlement case.

Which AI tool

an unnamed/unconfirmed AI tool. Note: Charlotin's public database records tool attribution only where a court order, brief, or reporting on the matter states it explicitly; "unidentified" or "implied" means the record indicates AI use but does not name a specific product — we do not guess.

Outcome

Fictitious citations undermined the reliability of Kostic’s affidavit evidence

How Citation Safe would have caught this

Citation Safe runs three deterministic layers before a brief is filed: (1) does the citation exist against CourtListener's database of published opinions, (2) if quoted, does that exact language appear in the source, (3) does the cited case actually support the proposition it is cited for. Fabricated case citations fail Layer 1. Fabricated or misattributed quotations fail Layer 2 even when the underlying case is real. Misrepresented holdings — a real case cited for a proposition it does not support — are the target of Layer 3. None of these checks involve asking another language model whether the citation looks right; they are lookups and text-matches against the actual source, which is why a hallucinated citation has to survive a direct lookup against the authoritative source — not another model's opinion — to earn a VERIFIED stamp; our measured false-verify rate is published live at /quality.

Check a brief before you file it → · See our live false-verify rate

Source: https://www.damiencharlotin.com/documents/3145/Kostic-v-Scott-Venturo-Rudakoff-LLP-2026-ABKB-626.pdf, via Damien Charlotin's public AI Hallucination Cases Database (CC0).