For the complete documentation index, see llms.txt. Markdown versions of documentation pages are available by appending .md to page URLs.
Skip to content

Claude Cowork Dashboard

In the product: https://app.revenium.ai/ai-assistants/claude-cowork, or Intelligence > AI Assistants > Claude Cowork.

The Claude Cowork dashboard shows what your teams spend on Cowork, who is spending it, whether sessions are getting cheaper, and what to change. Setup steps are shown on screen; this page covers what the dashboard needs, how it works, and how to read it.

What it needs

  • Claude Cowork telemetry, enabled once by an organization administrator as described in Set up Claude Cowork.

  • Departments, optional, to read spend and findings by department. See Attribute Spend to Departments.

  • A seat plan, optional. Cowork has no seat plan tab of its own; one plan and its seats cover Claude Code and Claude Cowork, and they live on the Claude Code dashboard under Claude Code > Seats & plan.

With no usage in the selected range, Overview and People show an empty state.

Reading the numbers

Overview: what changed, and what should we change?

Overview opens with what changed from the previous period: usage at API rates, active people, sessions per person and cost per session. What to change lists findings with their evidence and a suggested action. In Departments view a finding shows the departments it lands on; in People view it shows the people.

Claude Cowork dashboard with Overview and People tabs visible

What to change: what kinds of finding are there?

Each finding is a check on your telemetry. The checks fall into these families, and each finding states its kind of dollar:

Check family
Examples

Context

Context carried past 400K tokens, Cache rebuilt after a break

Model choice

Flagship model by default, Old model versions, a newer version reported cheaper per task

Kind of dollar
Meaning

saving on the seat bill

Seat cost you would stop paying each month, measured on your seat bill

gap to the team median

What these people spend above your team's median each month, a gap, not a saving that was measured

saving, estimated

An estimate of what could be saved, from your team's usage

saving if upgraded

What moving to the current model version would save, priced at API rates

needs inspection

Spend worth looking at; no saving is claimed

Checks that came back clean are listed under Looking good. Each check's explainer, threshold and how it is computed are shown on screen under its information icon.

Spend over time: is Cowork getting cheaper?

The chart has three modes:

  • Cost per session: is each session getting cheaper or dearer?

  • $ per million tokens: did the price of the work change, for example from a different model mix?

  • Spend and sessions: did volume or price move the total? Switch the line between Spend, Sessions and People active.

Who is spending: by department or by person

What you see below the chart depends on whether departments are synced:

  • With departments synced: Spend by department ranks the top departments by spend, each one including its teams, and groups the rest under Other; select a name to filter People to that department and its teams, or select ▸ beside it to see its teams and a (direct members) row for the people who sit in the department itself. When there are more departments than the card shows, See all … departments opens a searchable list of every department with spend in the period, a page at a time, and Back to the top … returns to the card. What to change offers Departments and People views, and anyone with no directory entry is grouped under No department.

  • Without departments: Spend by person ranks the top spenders, with everyone else grouped in one row, and the page header offers Departments: sync your directory.

Claude Cowork Cost by Model shows cost by model as Totals or Over Time; use Manage Columns to choose its columns.

People: who is driving the spend?

Select a person's name in Spend by person or on People to open their details: spend over time, any flag on their usage, and a token type breakdown you can expand by model. A flag such as Oversized context opens the matching finding on Overview. See all … people opens the People tab with everyone in the period.

On a finding's department breakdown, See people opens the People tab filtered to that department, including its sub-departments, and to that finding, sorted by that finding's spend; for Cache rebuilt after a break that is the Spent re-uploading column. The department and the finding show as chips at the top of the list; remove a chip to widen it.

Long conversations: who should we talk to?

The Context carried past 400K tokens finding opens the Conversation depth card. It groups assistant turns by how much context they carry and shows each group's share of turns and spend, then shows whose middle turn falls in each band, by person or by department. Use the card to decide whom to ask about the pattern; context size alone does not tell you whether the work was necessary.

The finding's own figure is what starting a new conversation from a summary each time one reached 400K would have saved, after paying for the extra summaries it would take, stated a month at this rate. A new conversation is assumed to open at your team's own median after the summaries Claude Cowork already carried in the last 30 days; a team with too few of them is given the median measured on Claude Code conversations across Revenium customers, and the finding's method says which one applied. Only turns of the main conversation count; helper agents are not counted in it yet. The newest days join the figure after the nightly refresh, and the period's first, partial day is not counted in it, so the month at this rate is scaled from the days the figure does count, and the finding's method names how many. A person whose extra summaries would cost more than they save counts as saving nothing, never as a negative, and the figure is the sum of its people. Opened from this finding, the People tab adds an Est. saving at 400K / mo column with each person's part of that same figure, on the same monthly basis, and the CSV download carries the same column.

Limits

  • Skill cost is currently an approximation and is not shown on this dashboard; it appears on Intelligence > AI Assistants > Skills. Use a skill's cost to compare skills and to see where spend concentrates, not as an exact amount.

  • Conversation depth needs telemetry with session and token data; without it the card shows an empty state.

  • Cowork usage is valued at API rates, not at your seat bill.

Last updated

Was this helpful?