Turning document dumps into a verified case chronology
Personal injury, employment, and insurance files arrive as hundreds of pages of medical records, emails, and reports, and someone has to turn them into a dated chronology before anyone can think about the case. Document summarization is a top-three legal AI use case at 74% — and running it as a repeatable batch process, with page-cite verification built in, is where the real hours come back.
You are a litigation assistant building a case chronology from documents I will paste in batches (medical records, emails, incident reports — anonymized). Process each batch the same way so results can be merged. Case issues to flag entries against: {{case_issues}} For the batch below, extract EVERY dated event into a table with columns: Date (YYYY-MM-DD) | Source document and page/paragraph | Event (25 words max) | People involved | Issue flag (from my list, or none) | Key language (short verbatim quote) Rules: - Include only events explicitly stated in the text. Never infer a date, fill a gap, or resolve an ambiguity — if a date is unclear or missing, use [UNDATED] and note why. - Where two documents conflict, record both entries and add a "CONFLICT" note describing the discrepancy; do not pick a side. - Quote key language exactly as written, including errors. - After the table, list: date range covered, documents processed, and any pages that appear to be missing from a sequence. Document batch: {{document_text}}
Fill in your details and the prompt updates live — then copy.
| Date | Source | Event | People | Flag | Key language | | 2025-04-02 | ER record, p. 14 | Presented to ER with acute lower back pain after workplace lifting incident | Patient; Dr. Reyes | notice; causation | "reports injury occurred at work this morning" | | 2025-04-19 | Email, p. 88 | Supervisor confirmed receipt of incident report | Supervisor Kim | notice | "we have your report from the 2nd" | | [UNDATED] | Incident report, p. 3 | Report form completed; date field blank | Patient | notice | — | CONFLICT: ER record states injury occurred "this morning" (4/2); incident report describes it as the prior afternoon.
The full workflow
- De-identify the batch or run it through a firm-approved tool with a business associate agreement where health records are involved.
- Feed documents in consistent batches and merge the tables into one master chronology.
- Spot-check every entry you'll rely on against the cited source page — AI drops and misdates events in long documents.
- Investigate each CONFLICT and [UNDATED] flag; these are often the case.
- Keep the verified chronology as the working reference for pleadings and depositions.
Watch out for
Medical records carry HIPAA obligations on top of privilege and confidentiality — never paste identifiable patient records into a consumer AI tool. De-identify first or use an enterprise tool with the right agreements in place.
Long-document accuracy degrades quietly: AI omits events and shifts dates without warning, so treat every entry as unverified until checked against the cited page — especially before it goes into a brief.
A chronology entry is not evidence; cite the underlying document, not the AI summary, and remember courts have struck filings (including expert declarations) built on unverified AI output.
Where this comes from
Every use case on this site is grounded in real reports from working lawyers — not invented by us.