Citations.law gives small-firm and solo lawyers deterministic citation verification, source-preserved legal research, and practice workflows at a fraction of legacy legal-research cost. CiteGuard's citation lookup is mechanical, not generative, and reports what the current corpus supports.
Documents are processed on Citations.law servers for citation extraction and verification. OCR, when needed, is sent to the service operator's configured Ollama endpoint. The standard deployment is intended to use service-controlled infrastructure, but configuration must be verified before relying on that deployment assumption. Raw uploaded documents are not retained after processing unless explicit raw-document retention applies in a separate documented workflow. Verification report HTML and audit metadata may be retained in the file cabinet when service-level report saving is enabled. Account or matter settings do not currently control /verify report saving. The service is designed to support lawyers' confidentiality obligations.
CiteGuard is the citation verification service within Citations.law — built for litigators who can't afford to cite bad law.
Supported case-reporter citations are checked against the disclosed current corpus. The lookup is deterministic and does not ask AI to decide whether a citation matches. Results remain subject to corpus coverage and lawyer review.
Documents are processed on Citations.law servers for citation extraction and verification. OCR, when needed, is sent to the service operator's configured Ollama endpoint. The standard deployment is intended to use service-controlled infrastructure, but configuration must be verified before relying on that deployment assumption. Raw uploaded documents are not retained after processing unless explicit raw-document retention applies in a separate documented workflow. Verification report HTML and audit metadata may be retained in the file cabinet when service-level report saving is enabled. Account or matter settings do not currently control /verify report saving. This data-minimizing design supports confidentiality obligations.
Upload opposing counsel's briefs, motions, or filings. CiteGuard scans supported case-reporter citations it detects and flags those not found in the current corpus — giving you a focused review list.
Paste text, upload Word documents, PDFs, HTML, or RTF. Scanned PDFs can be processed by the configured OCR endpoint — even photocopied filings work.
Get a structured verification report after processing completes. Each detected reference is marked verified, ambiguous, not in corpus, or unsupported. No ambiguity about what the tool is telling you.
21 million+ citation references from federal and state courts nationwide, built from authoritative public sources including the Caselaw Access Project and CourtListener.
CiteGuard is the first service, not the whole mission. Citations.law is becoming an indispensable legal workbench for solo lawyers, small firms, litigators, and specialty shops that need trustworthy research, drafting, and form workflows without legacy legal-research pricing.
Search source-preserved statutes, regulations, official forms, public filings, practice examples, and provenance cards. Start with litigation and NYC zoning, then expand by practice area.
Check opposing briefs, build authority maps, review motion papers, prepare case-law research memos, and generate cite-checked litigation work product.
Build toward tens of thousands of lawyer-ready forms, applications, agreements, claims, filings, and guided drafting templates by practice area.
For each form type, provide the five to ten key questions a lawyer needs to answer before drafting, filing, negotiating, or reviewing the document.
Use AI to draft, summarize, and revise while keeping answers citation-gated and source-mapped so lawyers can inspect the authorities behind the output.
Keep core access nominal at $25/month, then meter AI token usage separately for heavy drafting, document review, and large-volume legal work.
Three steps. No complexity.
Upload a brief, motion, filing, or memo. Or paste text directly. Supports Word, PDF, HTML, RTF, and plain text.
Supported case-reporter citations detected in the document are extracted and checked deterministically against our database of 21 million+ indexed references.
A clear verification report uses transparent labels: verified in the current corpus, ambiguous, not in corpus, or unsupported reference type. Lawyer review remains required.
Documents are processed on Citations.law servers for citation extraction and verification. OCR, when needed, is sent to the service operator's configured Ollama endpoint. The standard deployment is intended to use service-controlled infrastructure, but configuration must be verified before relying on that deployment assumption. Raw uploaded documents are not retained after processing unless explicit raw-document retention applies in a separate documented workflow. Verification report HTML and audit metadata may be retained in the file cabinet when service-level report saving is enabled. Account or matter settings do not currently control /verify report saving. This data-minimizing architecture is designed to support lawyers' confidentiality obligations; it does not guarantee a legal privilege determination or eliminate all risk.
The verification engine is deterministic — it doesn't use large language models to make judgment calls about your citations. It uses mechanical lookup against a known corpus of published court decisions. If it's not in the database, we tell you honestly — we never call absence "fake."
CiteGuard checks supported case-reporter citations against a disclosed, current corpus. A match does not establish positive treatment or complete legal research; absence is not proof of invalidity.