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 prose to tighten. Include citations and quotations exactly as they appear.
Determines which qualifiers are cowardice and which are load-bearing accuracy.
How hard to cut. Aggressive and above will start costing you nuance.
Terms of art, defined terms, or negotiated language that cannot be touched.
Style or citation conventions that override the editor's defaults.
Watch for these throughout
The model will quietly "tighten" material inside quotation marks. Diff every quoted passage against the source before filing.
Terms of art look like padding to an editor. Confirm that phrases like "willful and wanton," "specific intent," and "material adverse effect" survived intact.
Some qualifiers are required by Rule 11 or your duty of candor. Cutting "we believe" or "on the present record" can convert an argument into a representation.
Do not paste privileged or client-confidential drafts unless your firm's AI policy and the engagement terms permit it.
Word counts from the model are estimates. Run the real count in your word processor before relying on it for a limit.