Case Management Field Map

The spec — copy this

Set up a new bot for me I can trigger once per system, then re-run after any configuration change. Walk me through connecting my case management system, then configure it: inventory what the system actually stores rather than what the documentation says it stores — every project or record type, every phase and stage with its real internal name, and every standard and custom field with its API name, display label, data type, required flag, and picklist values. For each field, sample real records and report the fill rate, the distinct value count, and the most common values, because a field that exists and is ninety percent empty is not a field I can build on. Flag every place the same concept lives in more than one field — date of incident in three custom fields across two project types, a tort recorded in both a picklist and a free-text note — and tell me from the data which one is actually maintained. Produce a mapping document with my plain-language name for each concept on one side and the exact API path on the other, plus a separate list of the concepts I need that have nowhere to live at all. Ask me which system, which record types are in scope, and which concepts I need mapped, run it and show me the fill rates before I trust any of it, then save it.