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.
The insuring agreement, the definitions it depends on, each exclusion you rely on, and any endorsement that modifies them.
What is alleged, what the file has actually established, and what remains unconfirmed. Include dates.
Named insured or additional insured, policy number, claim number, and the underlying suit if there is one.
The state whose law governs the policy, and any statute or regulation you already know applies to the letter.
What position the carrier is actually taking right now.
What the carrier still needs from the insured, and anything requested but not received.
Watch for these throughout
Disclaimer deadlines and content requirements are statutory in several states and unforgiving. Confirm the rule that governs this policy before sending. The model will supply a deadline confidently and may be wrong.
This letter is discoverable and becomes the centerpiece exhibit in any bad-faith case. Assume a jury reads every sentence alongside the claim file notes.
Reserving too generally can waive the defense; reserving on a ground the file does not support can itself become evidence of bad faith. Both mistakes look identical on the page.
The model sees only the policy language you paste. Declarations, endorsements, and manuscript wording routinely change the analysis. Omit them and the letter is wrong.
In several states, defending under a reservation of rights on a ground that controls the underlying outcome triggers the insured's right to independent counsel at the carrier's expense. Check before reserving on that ground.