Law Onboarding Document Tracker

Goal

Create a structured tracker (CSV/MD/optional JSON) for each new client matter showing which onboarding items are present or missing, who is responsible, the next follow-up date, the nearest deadline, and a concise one-line status summary.

Inputs to gather

• Root folder path(s) containing client/matter files (to scan for documents).
• Calendar deadlines source: .ics export or list (CSV/JSON/MD with Client, Matter, Date, Label) – needed to link deadlines.
• Responsible-staff mapping per item type and any per-matter owner overrides (to assign owners).
• Timezone (for correct date calculations).
• Follow-up interval in business days, default 3 (drives next follow-up).
• Deadline buffer days before a due date, default 2 (adjusts follow-up near deadlines).
• Required onboarding item set beyond defaults, if any (to know what to look for).
• Matter naming conventions or sample folder names (to parse client vs. matter).
• Output destination path and preferred formats (CSV, MD, JSON).

Before doing any work, ask the user for these inputs in ONE message. Skip anything they already provided. If they tell you to decide, choose sensible defaults and say what you chose.

Workflow

1. Confirm the provided inputs and echo the assumed defaults; get user approval.
2. Define the data model with columns: Client, Matter, Signed Agreement, Intake Form, Client Email, ID Document, Missing Items, Responsible Staff, Next Follow-up Date, Nearest Deadline, Status Summary, Source Paths.
3. Inventory clients and matters:
   a. Use Read to list directories/files in each root path.
   b. Derive Client and Matter names from folder structure or ask for mapping if ambiguous.
   c. Collect filename, extension, modified time, and full path for every file per matter.
4. Classify documents: decide whether each file matches a required item via filename patterns and light content inspection; prefer the most recent “signed/final” version when multiples exist. Mark uncertain items as “Review”.
5. Parse deadlines:
   a. If .ics, load events and match to matters via name or tags.
   b. If list, read rows.
   c. Store the nearest future onboarding-relevant deadline (date + label) per matter.
6. Identify missing items by comparing found documents to the required list. Populate Missing Items as a comma-separated string; leave blank if none.
7. Determine responsible staff: apply the mapping per item type, override with per-matter owner file if supplied, then choose a primary owner using the priority Intake Coordinator → Paralegal → Attorney.
8. Compute Next Follow-up Date using business-day math:
   • If any items missing: earliest of (today + follow-up interval) or (nearest deadline – buffer days).
   • If none missing: (nearest deadline – buffer days) or “Complete” when no deadline.
   • If a missing item is already past due, label Overdue and set follow-up to today.
9. Generate the Status Summary string:
   “Status: Complete|Waiting on X|Overdue X. Owner: Name. Next follow-up: YYYY-MM-DD or Complete. Nearest deadline: YYYY-MM-DD – Label or None.”
10. Produce outputs:
    a. Use Edit to write tracker.csv with one row per matter.
    b. Write tracker.md grouped by Overdue, Waiting, Complete; include bullet links to documents and deadlines.
    c. If requested, write tracker.json mirroring the CSV schema.
11. Validate: spot-check at least three matters, note any ambiguous files, unmatched events, or parsing issues in a “Needs Review” section at the end of tracker.md.
12. Summarize actions and next steps, listing created/updated files.

Output

1. tracker.csv – tabular data following the defined columns (UTF-8, comma-separated).
2. tracker.md – human-readable summary grouped by status, with bullet links, a “Needs Review” section, and a brief changelog.
3. (Optional) tracker.json – JSON array of matter objects identical to CSV content.