Requests for Admission Drafter
Draft Requests for Admission aimed at single facts the record already supports — one fact each, grouped by issue, plus authentication RFAs and the facts you still need.
What is an AI requests for admission drafter prompt?
It is a CITE prompt that asks an AI tool to draft from case records or discovery responses. Draft Requests for Admission aimed at single facts the record already supports — one fact each, grouped by issue, plus authentication RFAs and the facts you still need. You fill in four fields; the Evidence block requires a page:line, Bates, page, or timestamp cite for every finding so a person can check each one against the record.
Sample prompt
Synthetic data
Synthetic example: The names, dates, case details, and issues below are fictional CasePrompts sample values, not client data or evidence from a real matter. They demonstrate the prompt format, not the accuracy of any AI model's output.
Preview the complete sample prompt
CONTEXT: You are a litigation support analyst assisting plaintiff's counsel in a trucking liability matter. Plaintiff's counsel is preparing Requests for Admission to serve on the motor carrier. The facts that matter are: the driver was on duty and over hours; the carrier skipped the pre-trip inspection; the load exceeded the rated weight. The attached record is what supports them. INSTRUCTIONS: Working only from the attached record, draft Requests for Admission: 1. Direct each request at a SINGLE fact the record already supports, phrased so that a denial would be contradicted by that record. 2. Keep each request plain and unqualified — one fact, no compound or argumentative requests, no defined terms the reader must chase. 3. Group the requests by issue under the driver was on duty and over hours; the carrier skipped the pre-trip inspection; the load exceeded the rated weight. 4. Add a short set of authentication requests for the key exhibits ("Admit that Exhibit __ is a true and accurate copy of …"). 5. For your own file, note the cite that backs each request — this is not part of what gets served. TEMPLATE — format your output exactly as follows: ## Requests for Admission — by issue | RFA # | Request (a single fact) | Supporting cite (work file) | Issue | |---|---|---|---| ## Authentication requests | RFA # | Request | Exhibit | Cite | |---|---|---|---| ## Facts you want admitted but the record does not yet support Each with the issue it serves and where the support would have to come from. EVIDENCE REQUIREMENTS: For every finding, identify the source document by name and cite page:line for transcripts, timestamps for audio/video, and Bates/page for documents. Draft a request only where a specific cite supports the fact; anything the record does not yet support belongs in the final section, not in a served request — write "not found in the record." Do not combine two facts into one request, and do not assume an exhibit's authenticity the record does not show. 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.
Through the Civil / insurance defense lens
Maintain a neutral, evaluative tone appropriate for carrier reporting; keep established facts and the plaintiff's contentions visibly separate throughout.
Through the Commercial litigation lens
Tie every factual premise to a document with a Bates cite; recollection unsupported by the record gets flagged, not adopted.
Through the Criminal defense lens
Build examination sequences that commit witnesses to specifics before any confrontation, and never embed a factual premise the discovery does not contain.
Through the Employment litigation lens
Build examination sequences that commit decision-makers to the reasons and the timing before any confrontation with the documents.
Through the Family law lens
Keep the tone measured and factual; inflammatory framing reliably backfires in family court, and specificity does the persuading.
Through the Medical malpractice — defense lens
Keep established chart facts and the plaintiff's allegations visibly separate, and let the contemporaneous documentation carry the persuasion.
Through the Medical malpractice — plaintiff lens
Write toward the causation chain — each clinical decision linked to its consequence — with provider language quoted verbatim and no medical conclusions the record does not state.
Through the Personal injury — plaintiff lens
Write toward a coherent narrative of fault and harm; specificity about the client's documented losses carries the persuasion — never adjectives.
Through the Probate & estate litigation lens
Keep it factual and element-driven; probate courts reward precision over heat, and a clean record cite persuades where adjectives do not.
Through the Prosecution lens
Build examinations that establish elements through specifics and anticipate the defense themes the record itself suggests.
Through the Workers' compensation — claimant lens
Write toward the statutory touchpoints — notice, causal connection, restrictions, wage loss — with provider and employer language quoted verbatim.
Through the Workers' compensation — employer/carrier lens
Maintain a neutral, evaluative tone appropriate for carrier reporting, keeping established facts and the claimant's contentions visibly separate.
AI output is a starting point, not work product. Verify every citation against the record before you rely on it, file it, or send it.
What you'll fill in
- 01Your role
- 02Case typee.g., "trucking liability," "first-party property," "medical malpractice"
- 03Key issue(s) — 1 to 3e.g., "vehicle speed at impact; brake maintenance; visibility"
- 04Opposing party(optional)
Verification checklist
- Mixed / full case record: open each cited page:line, Bates, page, or timestamp location and confirm it supports the finding. The prompt asks: “For every finding, identify the source document by name and cite page:line for transcripts, timestamps for audio/video, and Bates/page for documents.”
- Discovery responses: open each cited Bates or page location and confirm it supports the finding. The prompt asks: “For every finding, cite the request/interrogatory number and the page or Bates number of the response.”
- Re-check every item labelled “not found in the record” against the full source; these labels flag gaps or judgment calls for a person to resolve, not proof of absence.
- A human reviewer must verify every material statement and citation against the source record before relying on or sharing the output.
Pro tip Lead with the requests backed by a document — those are the ones a denial can turn into a Rule 37 cost-shifting motion. Keep the unsupported facts out of what you serve.
Related verification workflow
Related templates
Demand Letter Facts Section
Draft the facts and damages narrative of a demand from the record itself — every sentence cite-backed, gaps flagged instead of papered over.
AI Deposition Outline Prompt from the Record
Turn the verified case record into a topic-based deposition outline with fact-locking goals, record-cited exhibits, conflict probes, and open-to-closed question sequences.
Interrogatory Answer Support Builder
Gather the record facts and cites that support each interrogatory answer — facts only, gaps flagged, so the attorney drafts from evidence instead of memory.