This page lists three turns, the messages you send to the AI one after another in the same chat, and then a check of the answer. Keep it open next to your chat. Each turn shows the next thing to paste, with the values you entered already filled in. Nothing is sent from this page, and your conversation stays in the AI tool you are using.
Paste the transcript or the excerpts, keeping page and line numbers as they appear.
Name, role, and whether they are adverse, your own, or a third party.
One sentence. The story every finding gets measured against.
Exhibits and their key language, so testimony can be checked against them.
The court and applicable evidence rules, which govern how each finding can be used.
Watch for these throughout
The model fabricates page:line cites, and confidently. Check every one against the certified transcript before designating or filing.
Errata sheets change testimony. Confirm you are working from the corrected transcript, and check whether the errata itself is worth using.
"I don't recall" is not a denial, and courts treat the two very differently at summary judgment. Watch for the model collapsing them.
Testimony subject to a sustained objection or an instruction not to answer may be unusable. Check the objection log before relying on any pull.
Deposition transcripts are usually confidential under a protective order. Confirm your firm's AI policy and the order's terms before pasting one.