# Legal time entry cleanup prompt: free ChatGPT template

> Turn rough time notes into clear billing narratives: the task, the subject and the purpose, without adding work you did not do or time you did not spend.

Source: https://learn.ynteractive.com/content/prompts/time-entry-description-cleanup-prompt · Updated 2026-10-02 · Free from Stepthrough (https://learn.ynteractive.com)

[Collections and billing](https://learn.ynteractive.com/content/prompts#job-collections-and-billing) · [Law](https://learn.ynteractive.com/content/prompts#industry-law) · Works in ChatGPT, Claude, Gemini and Copilot

Updated October 2, 2026 · By [Robert Breen](https://learn.ynteractive.com/content/about)

Use this when your time notes read like "call w/ client re stuff" and the invoice is due. Clients question vague narratives, and firms lose goodwill, or fees, over them. This prompt rewrites each rough note into a billing narrative that names the task and its purpose, and it keeps your minutes exactly as entered. It does not add work to a line, split time or round anything. Only the person who did the work can say what the work was.

**Have a professional review it.** This prompt helps you draft, not decide. AI can get the law wrong and doesn’t know your jurisdiction or your facts, so have a licensed attorney review anything legal before you send or sign it.

## The prompt

Copy it into ChatGPT (or Claude, Gemini or Copilot) and replace every `[BLANK]` with your own details. It uses the four parts from [Prompt Writing 101](https://learn.ynteractive.com/content/prompt-writing-101-role-context-task-format): Role, Context, Task and Format.

Copy prompt

```text
Role: You are a billing coordinator at [FIRM] tidying time entry descriptions for attorney review.
Context: Here are the raw entries for matter [MATTER], each with date, time in tenths of an hour and my rough note: [RAW ENTRIES]. Our billing style: [STYLE]. Words or details to leave out because they are privileged or sensitive: [LEAVE OUT].
Task: Rewrite each note as one narrative line that starts with a verb, names the task and says what it was for. Keep each date and time exactly as I gave it. Do not add any work, person, document or reason that isn't in my note. If a note is too thin to describe honestly, keep it and add "(ATTORNEY TO CLARIFY)" at the end. Don't combine entries.
Format: A table with columns Date, Time, Narrative, in the order I gave the entries, followed by one line saying how many entries need clarification.
```

## Fill in the blanks

**`[FIRM]`**

Your firm's name.

**`[MATTER]`**

The matter number or name, as on the invoice.

**`[RAW ENTRIES]`**

Date, time and rough note for each entry, one per line.

**`[STYLE]`**

Your narrative rules: past or present tense, level of detail, client-facing or internal.

**`[LEAVE OUT]`**

Names, topics or strategy that must not appear on an invoice, or "none".

## Example, filled in

**A made-up example** from the free lesson [Reply Faster to a Client Asking for a Case Update: ChatGPT for Small Law Firms](https://learn.ynteractive.com/content/chatgpt-client-case-update-email-law-firm). Harbor Street Law is the made-up law firm from the case-update lesson. A billing coordinator cleans up a paralegal's rough notes for the matter's monthly invoice. All entries are invented.

Copy example

```text
Role: You are a billing coordinator at Harbor Street Law tidying time entry descriptions for attorney review.
Context: Here are the raw entries for matter 2026-114 Reyes Tile Supply, each with date, time in tenths of an hour and my rough note: 9/22, 0.4, call w/ client re invoices; 9/23, 1.2, draft letter; 9/24, 0.3, email; 9/25, 0.6, review docs. Our billing style: past tense, one line, client-facing. Words or details to leave out because they are privileged or sensitive: do not mention settlement ranges.
Task: Rewrite each note as one narrative line that starts with a verb, names the task and says what it was for. Keep each date and time exactly as I gave it. Do not add any work, person, document or reason that isn't in my note. If a note is too thin to describe honestly, keep it and add "(ATTORNEY TO CLARIFY)" at the end. Don't combine entries.
Format: A table with columns Date, Time, Narrative, in the order I gave the entries, followed by one line saying how many entries need clarification.
```

## What a good answer looks like

- Entry one reads like "Telephone conference with client regarding outstanding supplier invoices."
- Entries for "email" and "review docs" tagged ATTORNEY TO CLARIFY instead of filled with invented detail.
- 0.4, 1.2, 0.3 and 0.6 untouched.
- A closing line such as "3 entries need clarification."

## How to check it before you use it

An AI draft can sound right and still say something you never told it. Use the habit from the [Reply Faster lesson](https://learn.ynteractive.com/content/chatgpt-reply-to-customer-emails): check every promise, name, date and number against what you gave it before anything goes out.

- Total the times before and after. They must match to the tenth.
- Have the person who did the work approve every narrative. A tidy sentence can still describe the wrong task.
- Search the output for anything on your leave-out list.
- Check any limits in the engagement letter or the client's billing guidelines. This prompt doesn't know them.

## Why this prompt works

The value of a billing narrative is that it is true and specific. A model can improve the wording of a true note, but it cannot recall what you did, so the thin ones go back to a person.

## Practice it in the free lesson

**[Prompt Writing 101: Role, Context, Task, Format](https://learn.ynteractive.com/content/prompt-writing-101-role-context-task-format)**: Ask ChatGPT for the same customer email twice, once vaguely and once with a four-part prompt, and see exactly why structure gets a better answer. You do every step yourself in a practice copy of ChatGPT, and nothing touches your real accounts.

[Start the free lesson](https://learn.ynteractive.com/modules/prompt-writing-101)

Also useful: [Reply Faster to a Client Asking for a Case Update: ChatGPT for Small Law Firms](https://learn.ynteractive.com/content/chatgpt-client-case-update-email-law-firm)

## Terms used here

[Human in the loop](https://learn.ynteractive.com/content/glossary/human-in-the-loop) · [Redaction (masking private details)](https://learn.ynteractive.com/content/glossary/redaction) · [Audit trail](https://learn.ynteractive.com/content/glossary/audit-trail) · [Hallucination](https://learn.ynteractive.com/content/glossary/hallucination)

## Related prompts

- [Invoice email prompt](https://learn.ynteractive.com/content/prompts/invoice-email-prompt): Write the short email that goes with a new invoice: what the work was, the amount, the due date and how to pay, using only your…
- [Engagement letter draft prompt](https://learn.ynteractive.com/content/prompts/engagement-letter-draft-prompt): Draft an engagement letter from your own approved terms: scope, exclusions, fees and client duties. Gaps get flagged for review…
- [Payment reminder email prompt](https://learn.ynteractive.com/content/prompts/payment-reminder-email-prompt): A four-part prompt for a friendly first reminder on a late invoice: invoice number, amount, due date and ways to pay, with no…

## More collections and billing prompts

- [Nonpayment cancellation warning email](https://learn.ynteractive.com/content/prompts/nonpayment-cancellation-warning-email-prompt): Warn a client their policy is set to cancel for nonpayment: the amount, the deadline and how to pay, taken straight from the…
- [Payment plan offer prompt](https://learn.ynteractive.com/content/prompts/payment-plan-offer-prompt): Turn the installment plan you've decided on into a clear offer email, with the schedule copied exactly and a built-in check that…
- [Payment received thank-you prompt](https://learn.ynteractive.com/content/prompts/payment-received-thank-you-prompt): Confirm a payment and say thanks in a few lines: the amount, what it was for, the balance now owed, and what happens next…

[All free prompt templates](https://learn.ynteractive.com/content/prompts) · [AI glossary](https://learn.ynteractive.com/content/glossary)
