Skip to main content
When AI spend lands on a provider invoice, it arrives as a single line item with no client attribution. Without a way to tag that cost at the source, it falls into overhead — and recovering it from clients requires manual reconciliation after the fact. Parlé solves this by letting you attach your firm’s own matter number, engagement code, or billing reference directly to each project. In the app the field is called Project code — most firms use it as their expense or billing code, which is how this page refers to it. The code appears beside the project’s spend in the Usage report and its CSV export, so the AI cost reaches your billing system already labeled.

Setting a Project Code

You can set a project code when you create a project, or add one at any time afterward.
1

Set the code at project creation

On the New project form, enter your code in the Project code (optional) field. Setting it now means the project is coded from its first export.
2

Add or change the code later

Open the project and select the Project Details tab. Edit the Project code (optional) field and select Save. Clear the field to remove the code. Project Admins and Org Admins can edit it; everyone else on the project sees it read-only.
A project code is free-form text, up to 64 characters — Parlé does not check its format. Use exactly the format your billing or matter management system expects. The same code can be used on more than one project, for example several workstreams under one cost centre: Parlé points it out when you type a code that another project you can see already uses, but does not stop you, and spend is reported under the same code for each of them.
There is no required format. Use whatever matches your billing system:

Engineering code

ENG-4417

Client matter

ASHWORTH-MA

Project number

2024-PROJ-001
If your firm uses a matter number format (e.g. 12345.001), use that exact format so the CSV import into your billing system requires no transformation.

How the Code Flows

The code belongs to the project, not to individual messages. You do not need to re-enter it or tag individual conversations — every conversation in the project is reported under the project’s code. On the Usage screen, grouping by project adds a Project code column to the Breakdown table, and the CSV export carries the same value in a Project Code column. Feed that export into your billing system and the AI cost appears alongside other client expenses, already coded, with no manual matching required.
A report shows the code the project has when the report is run. If you change a project’s code mid-engagement, every export you download afterwards — including one covering earlier months — shows the new code, and exports you downloaded before the change keep the old one. If an engagement moves to a new matter number and the two need to stay separate, start a new project for it rather than re-coding the existing one.

Exporting by Project Code

1

Open Usage

Select Usage in the main sidebar. The Usage screen is for Org Admins.
2

Group by Project

Set Group by to Project. The code column is included only on a project grouping, because no other row is a project.
3

Choose your date range and projects

Select the range and filter to specific projects if needed. Leave the project filter empty to export all projects.
4

Download CSV

Select Download CSV above the breakdown table.
The export has one row per project, followed by a TOTAL row for the whole period — don’t sum the Cost column without excluding it. Each row carries the project’s code in the Project Code column, its cost in the Cost column, and the currency that cost is in — your organization’s reporting currency — in the Currency column.
The file identifies a project by its code, not its name. The Group column holds the project’s internal identifier rather than its name, and personal conversations are grouped as personal. A project with no project code has an empty Project Code cell and nothing else in the file to recognize it by — so set a code on every project you intend to reconcile.
Read the columns by their header names rather than by position: some columns appear only when there is something to report, so a column’s position can differ from one export to the next. See Usage Analytics for every column, and Currencies and Exchange Rates for how the reporting currency is chosen.