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.
What the case is about, the claims and defenses in play, and where it sits procedurally.
Your party and their posture in the case.
Where this is tried and what law supplies the elements.
Documents, testimony, and admissions, with exhibit numbers and page-line cites where you have them.
Who decides. A theory built for twelve strangers is not the theory you argue to an arbitrator.
What the other side says the case is about, if you already know from their filings or their opening in a related matter.
Watch for these throughout
A theory that requires the fact-finder to disbelieve unrebutted testimony or ignore an admitted document is not aggressive, it is unwinnable. Test each pillar against what the other side has already locked in.
The model will invent exhibit numbers and deposition page-line cites that look correct. Verify every record cite against your exhibit list and transcripts before any of it reaches an opening.
Three pillars is the cap. Each pillar past three costs the fact-finder's memory of the first three.
The theory that plays to a jury is rarely the theory that plays to a judge on a bench trial or a three-arbitrator panel. Confirm the fact-finder before you commit.
Case theory is core work product. Do not paste privileged strategy or client-confidential facts unless your firm's AI policy and the engagement terms permit it.