Skip to content
Extract from the recordDeposition transcript

Trial Designation Puller

Pull proposed deposition designations on your issues with page:line in/out points, verbatim anchors, and a colloquy-cleanup flag on every range.

Report a correction

What is an AI trial designation puller prompt?

It is a CITE prompt that asks an AI tool to extract specific items from deposition transcripts. Pull proposed deposition designations on your issues with page:line in/out points, verbatim anchors, and a colloquy-cleanup flag on every range. You fill in five fields; the Evidence block requires a page:line 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
Customize in builder
CONTEXT:
You are a litigation support analyst assisting defense counsel in a premises liability matter, preparing trial designations. The attached document is the certified deposition transcript of Olivia Tran, store manager on duty at the time of the fall. The issues to designate on are: inspection schedule compliance; notice of the substance.

INSTRUCTIONS:
Identify every passage of testimony that substantively addresses the specified issues and propose it as a designation. For each proposed designation:
1. Give precise in and out points in page:line form, beginning at a question and ending at the completion of an answer.
2. Quote the first and last few words of the range verbatim so the boundaries can be verified instantly.
3. Flag any objections, colloquy, instructions, or sidebar discussion inside the range that will need cleanup or a ruling.
4. Note in one sentence what the designation establishes.
Keep ranges tight — designate the exchange that proves the point, not the surrounding examination.

TEMPLATE — format your output exactly as follows:
## Proposed designations
| # | Issue | Range (page:line in – out) | Opens with… / ends with… (verbatim) | Colloquy flag | What it establishes |
|---|---|---|---|---|---|
## Cleanup list
| Range | What needs attention (objection / colloquy / instruction) | Cite |
|---|---|---|

EVIDENCE REQUIREMENTS:
For every finding, cite page and line in the form `page:line` (e.g., 47:12–48:3) and quote the operative testimony verbatim. The in/out anchors must be verbatim transcript text. If an issue has no designable testimony, write "not found in the record" for that issue rather than stretching a range to cover it. Counter-designation strategy and admissibility are attorney calls — do not opine on them.

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.

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"
  • 03Witness / deponent namee.g., "Witness A" or "the treating physician"
  • 04Their role in the casee.g., "plaintiff's accident reconstructionist"
  • 05Key issue(s) — 1 to 3e.g., "vehicle speed at impact; brake maintenance; visibility"

Verification checklist

  1. Deposition transcript: open each cited page:line location and confirm it supports the finding. The prompt asks: “For every finding, cite page and line in the form page:line (e.g., 47:12–48:3) and quote the operative testimony verbatim.”
  2. Compare every verbatim quotation word for word with the source.
  3. 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.
  4. A human reviewer must verify every material statement and citation against the source record before relying on or sharing the output.

Pro tip Run it per witness, then merge the tables — the colloquy flags become your pretrial-conference punch list.

Related verification workflow