Evaluating exposure, testing causation, and developing comparative fault and mitigation — often with carrier reporting in mind. Every prompt on this page carries that emphasis. Pick a workflow and add only the details the assignment needs, using neutral labels where possible.
The Civil / insurance defense lens adds this practice context to every template: This work product supports the defense: evaluating exposure, testing causation, and identifying comparative fault, alternative explanations, and failures to mitigate.
Here is one complete example: the “Comb the medicals: gaps, prior claims, compliance” workflow with medical records as the source. Run it on your own file in Ask your files, or copy it into an AI tool your firm approves.
Synthetic example: Names, dates, organizations, and matter details are fictional placeholders, not a real case record.
CONTEXT: You are a litigation support analyst assisting civil defense counsel in a motor vehicle negligence defense matter. The attached production is the medical records of Alex Morgan. The incident at issue occurred on January 15, 2025. The injuries and conditions that matter are: comparative fault; prior injuries; treatment gaps; claimed limitations. This work product supports the defense: evaluating exposure, testing causation, and identifying comparative fault, alternative explanations, and failures to mitigate. INSTRUCTIONS: Build a complete treatment chronology covering every encounter in the production — visits, imaging, procedures, therapy sessions, and telephone encounters. For each encounter capture: provider and facility; date of service; presenting complaints in the patient's words where recorded; objective findings; diagnoses exactly as stated in the record (do not supply diagnoses or codes the record does not state); treatment rendered; medications; work or activity restrictions; and the next-step plan. Separately and explicitly: 1. Flag every gap in treatment longer than 30 days. 2. Flag every reference to symptoms, injuries, or treatment pre-dating January 15, 2025. 3. Collect every causation statement — any provider language attributing or declining to attribute a condition to the incident — verbatim. In this engagement, additionally: Flag treatment gaps, missed or cancelled appointments, non-compliance notes, prior or subsequent injuries to the same body parts, and every reference anywhere in the records to prior claims, accidents, or litigation. TEMPLATE — format your output exactly as follows: ## Chronology | Date | Provider / facility | Complaints | Findings | Diagnoses (as stated) | Treatment / meds | Restrictions | Cite | |---|---|---|---|---|---|---|---| ## Treatment gaps (> 30 days) | Gap | Last visit before (cite) | First visit after (cite) | |---|---|---| ## Pre-existing / prior history references | Date | Provider | Verbatim reference | Cite | |---|---|---|---| ## Causation statements (verbatim) | Date | Provider | Exact language | Cite | |---|---|---|---| ## Compliance & prior claims (defense review) | Date | Type (missed appt / non-compliance note / prior claim or accident reference) | Verbatim record language | Cite | |---|---|---|---| EVIDENCE REQUIREMENTS: For every entry, cite provider, date of service, and the page or Bates number of the source record. Record diagnoses and causation language exactly as written — never normalize, upgrade, or infer a diagnosis, and never supply an ICD code the record does not contain. If a record page is illegible or an encounter is referenced but missing from the production, list it under a final heading "Missing or illegible — request from provider" rather than guessing at its contents. Unless a section above specifies its own marker, write "not found in the record" wherever the provided record does not support a requested finding. Do not infer or fill gaps from outside knowledge. The scope is limited to the requested task, stated issues, and provided record. Do not introduce outside subjects or sources. A human reviewer must verify every material statement and citation against the source record before relying on or sharing the output.
Every template in the library assembles like this with the Civil / insurance defense lens: open the builder and add only the assignment details needed, using neutral labels where possible, or read the Attorney's Guide to AI Prompting for the method behind it.
Each pairs one template with this practice’s emphasis, end to end.
Read the general guide for each workflow below. To apply the Civil / insurance defense context to your own facts, use the builder actions above.
Align a witness's deposition against every prior statement, classify each conflict, and get a lock-in → confrontation cross sequence with dual cites.
Audit an expert's deposition against their report: new opinions, abandoned opinions, changed bases, and undisclosed reliance materials — the record a motion to exclude depends on.
The standing-rules prompt: paste this once at the start of a chat session and every answer after it comes cited, sourced, and honest about gaps.