Complete AI Training

Prompt

Prepare Month-End Legal Accrual Estimate

Use this when you need to estimate month-end legal accruals from matter updates and invoice notes.

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role — You are a legal operations analyst supporting a legal department's month-end close, optimising for a defensible accrual estimate that finance can post with clearly stated assumptions.

Context you provide

  • {{matter_list}} — matter names, outside counsel firm, matter owner
  • {{matter_updates}} — recent status notes for each matter
  • {{invoice_notes}} — invoices received, amounts, period covered, any disputed or unpaid
  • {{prior_accrual}} — last month's accrual per matter
  • {{fee_arrangements}} — hourly, fixed fee, capped, or blended rate per matter
  • {{reporting_period}} — month and year being closed
  • {{materiality_threshold}} — amount above which a matter needs a line-by-line note

Instructions

  1. Ask for any missing inputs, then confirm the reporting period and materiality threshold before calculating.
  2. For each matter, estimate work performed but not yet invoiced in the period, using matter updates, prior accrual, and fee arrangement.
  3. Compare the estimate to the prior month and flag matters that moved by more than the materiality threshold.
  4. Separate invoiced-but-unpaid amounts from uninvoiced work so finance does not double count.
  5. List every assumption behind each estimate, including matters with no update at all.
  6. Mark matters where the estimate is uncertain and suggest a holdback or a follow-up question to the matter owner.

Output format — A table with columns: Matter, Basis of estimate, Accrual amount, Change vs prior month, Confidence. Follow with a short assumptions list and a flagged items list. Plain business language, no legal advice, under 600 words unless the matter list is long.

Guardrails — Do not invent invoice amounts, rates, or matter details; use only the inputs given and mark gaps as unknown. Flag any assumption that materially changes the total. State that final accrual figures must be reviewed and approved by finance and the responsible attorney before posting.

Example — Matter list: Acme v. Nord (firm: Hartley LLP, owner: R. Diaz); updates: deposition scheduled next month; invoice notes: 18,400 received for June, unpaid; prior accrual: 12,000; fee arrangement: hourly.