Templates & Autofill

Placement is exact and deterministic: you set a field’s position, size, and page on the canvas, and autofill stamps the value at that same spot every run.

AI extraction reads each file and returns one value for every extracted input you define, and only those. A field can define more than one, each with its own rule. When a value comes back wrong, add an instruction to steer the next run.

A computed output derives a value with a deterministic JSON expression (arithmetic, string work, date math, and conditionals over other case-data values) that re-evaluates live in the case detail and again at document generation, with $today and $now keeping date math current without re-extraction.

Bindings stamp values from outside the case (today's date, or your company profile) onto generated output at fill time; they resolve at generation and are never stored in case data. Values that arrived with the file are not bindings: those are delivery inputs.

Source tabs in the document bar assemble a template's output from ordered workspace document sources, blank pages, and an optional form; Document reflows lets fill re-find each field's anchor when the document layout shifts.

A template can define an output filename pattern with {token} placeholders; generated PDFs land as their own row in the case Documents list, tagged with the template output category and named by that pattern.

Batch templates fill one row-repeating document against many cases at once, while a "Run with your documents…" run fills any template against your own PDFs; on Free and Lite that run is saved as a temporary case.

Open a file in the case review modal, pick a template in the right-side Autofill rail, click Autofill, and the finished PDF lands as its own row in the case Documents list, tagged with the template output category.