Analytics


URL	`/analytics/users`
Sidebar	Analytics → Users
Needs	Analytics · View
Requires	Enabling per organization · gated — contact support

Users shows activity per developer — what they ran, what it cost, and how their agent runs went.

Users needs Analytics · View.

What’s on the page

Headline figures

Four cards across the top, covering everyone the current filters match rather than the page on screen.

Card	Shows	Underneath
Active Users	Developers with activity in the range	How many tasks they worked on
Tokens Used	Tokens across those developers	How many developers that is
Agentic Users	Developers whose clean completion reaches Steady or better	The average clean-completion rate across developers with enough runs to score, as N% avg strength — or Awaiting run signal
Peak User (Tokens)	The largest single consumer’s token count	Their email address. Selecting the card opens their page

Table

Headed Users with the total count.

Column	Contents
Name	The developer, with their email
Longest Hands-off Run	The longest single AI turn that ran without user input · sortable
Median Run	The typical AI-turn length · sortable
Clean Completion Rate	The share of turns that ended in a clean completion rather than a request for clarification, an error, an interruption or an unrecorded outcome, badged Power, Steady, Emerging or Light · sortable
Total Cost	Estimated spend · sortable
Total Tokens	Tokens used · sortable
Tasks	Tasks worked on · sortable
Models	How many distinct models were used · sortable
Policy Enforcement Count	Blocks, Slack approvals, warnings, audits and skill injections in the window · sortable. Under an enforcement filter the task and enforcement counts read matching against total, such as 2 / 7. Hover for the breakdown by type — Data, MCP, Terminal, Skills — and outcome

Twenty developers to a page. An info icon on each of the three run-quality headers explains what the number measures, and a column picker chooses which of Total Cost, Total Tokens, Tasks and Models are shown.

Filters and controls

Time range

The standard Analytics range selector applies.

Filters

Filter	Values
User	The people you can read
Tool Type	The AI tools your organization uses
Department	Departments in your organization
Team Manager	Managers in your organization
Policy Enforcement	Keeps the Policy Enforcement Count to the enforcements you pick; with none picked it counts them all. The panel is the one described on Tasks — By Policy Type cells or By Policy Name — and its counts here are enforcements, not tasks. The choice shows as a chip in the page header

Search users by name or email… narrows the table.

What you can do

Action	Result
Sort a column	Orders every developer by that measure, not just the page on screen
Select a developer	Opens their own page at `/analytics/users/[userId]`
Export CSV	The developers matching your current filters, from the Export Users dialog · Analytics · View with Organization scope

A developer’s page

Total Cost, Total Tokens, Total Tasks and Avg Cost/Task for the range, a Model Usage by Cost breakdown showing what share of their spend each model took, and their tasks - with the work type editable on your own tasks, and never at Analytics · View. Their tasks are listed with:

Column	Contents
Started At	When the task began
Task	What the agent was asked to do
Work Type	The category of work
Tool Used	The AI tool that ran it
Duration	How long it ran
Tokens	Tokens used
Cost	Estimated spend
Enforced By	The policy enforcements that acted in the task

A Recent chip, a day picked on the heatmap and the Policy Enforcement filter all narrow the list; Clear date filter drops the day. A Token Breakdown splits their tokens into Input, Output and Cache. Where personal-account visibility is on for your organization, an Accounts card lists the vendor accounts they have signed in with: the tool, the account (or No sign-in detected where it was used without a sign-in that could be read, such as an API key or a gateway), a Personal badge for a personal account on a managed device, and the plan with a since date. Under Activity & Agentic Use sits the run-quality picture: weekly trends for clean-completion rate, median run and longest hands-off run, and an activity heatmap that always covers the last 12 months regardless of the range you picked, shaded Less to More with No activity on empty days. A developer with too little activity to score reads Insufficient signal, and a trend needing more weeks reads Not enough weekly data to draw a trend yet.

Longest hands-off run and Clean completion rate show how much your developers trust their agents. Both rising usually means the policies and setup are working.

Run-quality figures stay blank until a developer has enough agent runs in the window for the number to mean something: a developer with some runs but too few to score reads as a dash. A developer with no agent runs at all reads as zero, badged Light. To read either end of the distribution, sort Total Tokens — descending for your heaviest users, ascending for your lightest.

Messages you may see

Message	What it means
`No Users Found`	Nothing matches the current range, search and filters. Widen or clear them
`This List Could Not Be Loaded`	The request failed, so the empty table is not an answer. Refresh to try again, or clear the search
`No Tasks Found` · `These Tasks Could Not Be Loaded`	On a developer’s page: nothing matches, or the request failed and a refresh retries it
`Failed to update work type`	A work-type change made from a developer’s page was not saved
`This user could not be loaded` · `User not found`	A developer’s page could not be fetched, or the person does not exist. Refresh to try again
This usage is from an unmapped device	The usage came from a device not yet mapped to a person, so it shows under the device ID. An admin maps it with Import Devices in Settings → Devices, and the usage moves to that user

Page	For
Users	People, groups, policies and monitoring
Cost Management	Spend against limits, and exemptions

Getting Started

CLI

Policies

Integrations

MDM Integrations

Connections

Support & Troubleshooting

Analytics — Users

What’s on the page

Headline figures

Table

Filters and controls

Time range

Filters

What you can do

A developer’s page

Messages you may see

​What’s on the page

​Headline figures

​Table

​Filters and controls

​Time range

​Filters

​What you can do

​A developer’s page

​Messages you may see

​Related

What’s on the page

Headline figures

Table

Filters and controls

Time range

Filters

What you can do

A developer’s page

Messages you may see

Related