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 state and court, plus the guideline model if you know it: income shares, percentage of obligor income, or Melson.
The number your state's worksheet produced and every input that produced it. The model will not compute this.
Direction, target monthly figure, and whose position you are advancing.
The facts you would put in front of the judge, and what proves each one.
Paste the current statutory or rule text. Leave blank and the argument comes back with the factor slots empty rather than guessed.
Watch for these throughout
Deviation factors, findings requirements, high-income treatment, and parenting-time adjustments are set by state statute or rule and change. Read the current text yourself. Do not use any factor the model states without confirming it.
Never accept a guideline amount the model produces. Run the number through your state's own calculator or worksheet and treat the model's arithmetic as a draft to check.
An upward deviation request invites imputation of income to your client and scrutiny of their spending. A downward request invites a lifestyle audit. Weigh the exposure before filing.
Retroactivity and effective-date rules for support modification vary and can wipe out months of relief. Confirm them in your jurisdiction before advising the client what this is worth.
Do not paste the client's financial affidavit, medical records, or a child's IEP into a model without checking your firm's AI policy and any protective order in the case.