Review balances below approved retainer thresholds
Compare supplied balances with approved thresholds and show unbilled work separately.
Tools for the documented steps
Practice relevance
Cross-practice idea · A general operational method. Review the stated tool and jurisdiction limits before use.
The problem
Compare supplied balances with approved thresholds and show unbilled work separately.
Why it matters: A low balance and unbilled work describe different accounting facts. Keeping them separate gives finance and legal staff a clearer review list before deciding on any replenishment request or change in work.
Sources & evidence
Proposed / not tested. The public source describes the problem. Documentation supports only the stated method components; no result from this recipe has been verified.
What’s been verified
Source methods and reported problems have been reviewed. We have not run the adapted workflow. The sample below describes expected behavior on synthetic data, not a customer result.
What to measure: In a synthetic pilot, count correctly found exceptions, false alarms, and unresolved inputs. No time or cost saving is assumed.
- Pain evidence: Handling Unpaid Client Invoices ↗Handling Unpaid Client Invoices, 2026-02-01, older. OP says existing retainers were exceeded; a practitioner specifically recommends tracking uncollected time/costs against remaining funds. Distinct from A13: warns before an unpaid bill exists.
- Method: Clio evergreen management ↗Clio evergreen management documents minimum-balance notifications and trust-management reporting.
Source checked: October 15, 2026. Pain accounts are self-reported. Documentation supports components; this adapted recipe and prompt have not been tested. We wrote these prompts. The adapted workflow hasn’t been tested.
Suggested approach
Start when: Updated authorized ledger or threshold alert
- compare explicit balance/threshold and separately report unbilled work
- Keep source references and report unknowns instead of filling gaps.
- The responsible reviewer checks the report before any separately approved 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: Authorized finance/legal staff verify ledger, accounting treatment and engagement terms. Test client-level versus matter-level balances and two currencies.
What you need
Your firm-approved AI assistant · prepared files
- Clio Manage access to Trust management report and the approved matter/client scope.
- Firm-approved threshold policy, currency and current trust-balance evidence; this is a replenishment review only.
- 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
- Trust management reports current client/matter trust funds, unbilled amount and configured threshold. A configured threshold still needs firm approval before use.
- Client funds may not be allocated to a specific matter; no duplicate allocation, cross-client offset or automatic deduction of unbilled work is permitted.
Check access and setup
- Actual account access, plan and source-data completeness have not been tested.
Obtain the named report, with its real scope
Clio Manage; optional Manage AI report link · Diamond/gem > AI Launchpad > Ask a question; or Reports > Classic reports > Reports > Client > Trust management
If Manage AI is available, ask for the named report with the exact period, then open its report link. Otherwise use the native Reports menu shown. Set the actual filters, choose CSV under Output format and generate. Keep the original headers, filter settings, generation time and control totals. Inspect Client, Matter, Unbilled amount, Amount in trust, Minimum threshold and Amount below minimum. Capture actual generation time and whether each balance is client-level or matter-level.
- Expected output
- Native Trust management CSV and a saved scope/control note. The kit schema is a later staff mapping.
- Next step
- Inspect the actual report and source items before creating a separate deidentified workbook.
- Check before continuing
- Report/AI availability varies by plan and permissions. A returned link is not an arbitrary data-query result; verify the report name and filters.
Map the observed records to the starter input
Excel and authorized staff · Separate analysis workbook > Home > Format as Table
Create balances.csv. Map Amount in trust to balance and Unbilled amount to unbilled_work_amount only for the same verified scope. Record matter_alias,client_alias,currency,report_scope and as_of_date. Copy approved_threshold from the policy/approved configuration, checking the native Minimum threshold. Keep client-level balances separate from matter-level values; ambiguous allocation blocks the row. In Scope state whether the approved trigger compares current balance directly or a separately approved projection. Create named tables for Balances. Put the policy and review scope in visible worksheets or paste them into the next prompt.
- Expected output
- Balances table with an explicit scope for every amount and approved trigger rule.
- 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.
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 verified same-scope balances and thresholds, preserving separate client/matter records.
- Expected output
- Threshold exception queue with scope/approval gaps.
- 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.
Approve the review result
Final human reviewResponsible staff reviewer · Reviewed local worksheet
The bookkeeper checks the current account/matter balances and scope; the lawyer confirms the engagement and approved replenishment policy before any request.
- Expected output
- Reviewed threshold list, not authorization to withdraw or transfer funds.
- Next step
- Any external message, source change, payment or deletion requires its own authorized process.
- Check before continuing
- Never net one client’s shortage against another client’s funds, or treat unbilled work as an approved trust disbursement.
What you’ll get
Approved assistant workspace or Excel; internal threshold-review.csv only, never a payment request.
Inputs and a sample test Synthetic example · not a measured result
Input files
- balances.csv: matter_alias, client_alias, currency, report_scope, as_of_date, balance, approved_threshold, unbilled_work_amount. No banking/account details.
Synthetic example
M2 balance 1000 USD, approved threshold 1500 USD, unbilled 200 USD → below threshold by 500 USD; show unbilled 200 separately, no transfer or netting.
Expected output
M2 balance 1000 USD, approved threshold 1500 USD, unbilled 200 USD → below threshold by 500 USD; show unbilled 200 separately, no transfer or netting.
Test a failure
Authorized finance/legal staff verify ledger, accounting treatment and engagement terms. Test client-level versus matter-level balances and two currencies.
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 6 files
Instructions, blank templates and separate synthetic examples; these files do not install an automation. Blank templates still need verified source data.
- Download starter kit All inputs, synthetic examples and review notes in one ZIP. No automation is installed.
- Start here: get the sources and prepare the review Documentation-checked acquisition, explicit manual mapping, exact prompts and human review limits
- Setup and review checklist Required inputs, file use, review steps and limits
- Balances blank CSV Blank input headers for balances.csv
- Balances synthetic example Synthetic test records for balances.csv
- Synthetic example expected results Compare a pilot result with the planted exceptions
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.