Law Firm Agents
Client ServiceProposed workflow

Draft reminders for missing client documents

Compare a document checklist with receipt records before drafting one reminder.

Tools for the documented steps

These tools support separate parts of the method. The prompt does not connect them or verify a native integration.

Practice relevance

Cross-practice idea · Useful supporting administrative method; no claim of practice-specific legal instructions.

Scope: Clio Manage records and an Excel/Copilot draft queue. Staff check the missing-document list and approve any separate send.

The problem

Compare a document checklist with receipt records before drafting one reminder.

Why it matters: Missing documents can leave staff preparing a matter with an incomplete file. Checking receipt records before drafting a reminder also avoids asking clients for items they already supplied under another name.

Sources & evidence

Proposed / not tested. The public discussion supports the problem; the method source supports only the documented features. No outcome from this adapted recipe has been verified.

What’s been verified

The linked sources support the complaint and documented method components. We have not run this recipe or verified its results. The example below is synthetic, not a customer result.

What to measure: During the pilot, count findings confirmed by the reviewer, false alarms, and missing-input cases. Do not infer time or money saved.

  • Pain evidence: Slack clients ↗Slack clients, 2025-04-28, older. A family-law paralegal describes unresponsive clients and missing documents before final hearings. This is established-client collection, separate from intake.
  • Method: Clio for Clients actions ↗Clio for Clients actions documents messages, document uploads and notifications. Important: adding documents to a previously shared folder automatically shares them with that client.

Source checked: October 15, 2026. Pain reports are self-reported and identities are unverified. Method documentation supports components, not a tested end-to-end workflow. We wrote these prompts. The adapted workflow hasn’t been tested.

Suggested approach

Start when: Staff-set document request review date

  1. compare approved checklist with received-file metadata
  2. Keep row or page references and mark missing or ambiguous evidence. Do not apply the suggested changes.
  3. The responsible staff member checks the draft against the source records and approves any separate action.

Limits and review

The assistant drafts or reports only. Check source records and review the output before a human performs any separately approved send or change. No automatic legal decision, money movement, account connection or publication is included.

Who reviews it: Staff confirm material was not received under a different name; lawyer approves scope and urgency. Never place internal files in a client-shared folder. Test alias filenames and already-received items.

What you need

Your firm-approved AI assistant · prepared files

  • Actual lawyer-approved client document checklist and actual receipt records for a bounded matter.
  • Current approved secure-upload instructions and explicit requested due dates; no inferred deadline.
  • Firm-approved Excel; optional Copilot entitlement and tenant approval for the exact minimized data. Native Excel analysis can be done manually if Copilot is absent.
  • Keep raw exports and identifying source pointers in a separate restricted location. The AI workbook contains only approved alias-based tables and visible policy/scope text, never raw client records on another tab.
  • Use synthetic inputs first. Keep real data in firm-approved accounts and processing, with appropriate access, confidentiality and retention controls. Aliases alone do not anonymize records. Never paste credentials, API keys or unnecessary client details.

How to use

Documentation-checked proposed route; source collection and human approval required

Before you start
  • A document filename is not evidence that the requested item was supplied or sufficient. Receipt_status is a staff judgment after opening the actual receipt.
  • No universal client-checklist export or AI query is verified. This route explicitly reads maintained requests and receipts.
Check access and setup
  • Actual account access, plan and source-data completeness have not been tested.

  1. Inspect the real requests and receipts

    Clio Manage and local document viewer · Matters > selected matter > Tasks / Communications / Documents

    Read the actual approved checklist or request in Tasks/Communications. In Documents, inspect the actual received item and receipt history under firm procedures. If the source records are outside Clio, open those actual records locally; this route does not claim an export from that unidentified system.

    Expected output
    An explicit requested-item list and a separately verified receipt log.
    Next step
    Keep source references and identities restricted; prepare aliases and shareable descriptions.
    Check before continuing
    A portal upload, message acknowledgment or similar filename does not itself prove fulfillment.
    Step documentation 1 ↗

  2. Map the observed records to the starter input

    Excel and authorized staff · Separate analysis workbook > Home > Format as Table

    Create requested-items.csv with a stable request_item_id,matter_alias,approved_plain_description,supplied_due_date and secure_upload_instruction copied from the approved request. Create received-items.csv with receipt_id, an explicitly matched request_item_id_if_known,matter_alias,deidentified_filename and staff-verified receipt_status. Keep ambiguous matches unresolved. Put the approved reminder policy/cutoff in Scope. Create named tables for RequestedItems and ReceivedItems. Put the policy and review scope in visible worksheets or paste them into the next prompt.

    Expected output
    RequestedItems and ReceivedItems, with actual manually reviewed source evidence.
    Next step
    Check the mapping against each original source before using AI.
    Check before continuing
    Aliases and missing policy fields are staff-created; do not relabel a native export as the kit schema. Unknown stays blank/unknown, not false or zero.
    Step documentation 1 ↗

  3. Review the bounded evidence with Copilot

    Excel Copilot, optional · Approved analysis workbook > Copilot icon at lower right > Chat only

    Use Chat only and submit the prompt. Without Copilot: compare explicit item IDs and draft from approved descriptions after checking receipts.

    Expected output
    Missing-item review list and a lawyer-reviewable reminder draft.
    Next step
    Copy the draft exception list to the reviewer; retain row references.
    Check before continuing
    Check every flagged row and the scope. A fluent answer is not evidence of completeness; no automatic workbook or source-system edits.
    Step documentation 1 ↗Step documentation 2 ↗

  4. Approve the review result

    Final human review

    Responsible staff reviewer · Reviewed local worksheet

    Staff reopen the actual receipts, clear ambiguous matches and check the upload destination. The lawyer approves the exact outstanding items and wording before any client communication.

    Expected output
    Approved reminder draft or a hold for missing facts.
    Next step
    Any external message, source change, payment or deletion requires its own authorized process.
    Check before continuing
    Do not transmit a reminder based solely on filename comparison; no attachment or client identity goes to AI without specific firm approval.
    Step documentation 1 ↗

What you’ll get

missing-items.csv: request_item_id, receipt_ids, status, evidence_rows, approved_description, supplied_due_date; separate placeholder reminder. No live changes.

Inputs and a sample test Synthetic example · not a measured result

Input files

  • requested-items.csv: request_item_id, matter_alias, approved_plain_description, supplied_due_date, secure_upload_instruction. received-items.csv: receipt_id, request_item_id_if_known, matter_alias, deidentified_filename, receipt_status.

Synthetic example

DOC1: matching request ID under a different file name
DOC2: no receipt
DOC3: possible receipt with no matching ID

Expected output

DOC1: received, no reminder
DOC2: draft uses approved description and date
DOC3: uncertain, ask staff before chasing

Test a failure

Staff confirm material was not received under a different name; lawyer approves scope and urgency. Never place internal files in a client-shared folder. Test alias filenames and already-received items.

Try with the sample files

Follow the tool steps above and use the inputs named in each step. Where provided, native-* files are blank scaffolds and NATIVE-INPUT-MAPPING explains their fields. Original examples and the optional full review prompt use a separate prepared-input schema. Keep them separate unless the mapping explicitly connects them. Downloading a kit does not connect accounts or prove the workflow works.

Download inputs and checklist 8 files

Instructions, blank templates and separate synthetic examples; these files do not install an automation. Blank templates still need verified source data.

Optional full review prompt for prepared inputs

Prepared-input review prompt with Your firm-approved AI assistant · prepared files

Proposed / not tested · editorial prompt. This prompt uses the original prepared-input schema shown in the sample test. Step prompts may use different tables. Follow NATIVE-INPUT-MAPPING where supplied; do not mix the original examples with native-step inputs without mapping and checking every field.

Read original method Read pain evidence

Published by Law Firm Agents. These are source-linked editorial adaptations; no end-to-end execution is claimed. Read the plain-text version.