분석

Tagged API key ID.

Same measure as chat_metrics.distinct_conversation_connector_used_count, for activity recorded while members had Chat and Cowork unified turned on. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

Same measure as cowork_metrics.distinct_session_connector_used_count, for activity recorded while members had Chat and Cowork unified turned on. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

Number of distinct conversations in which the connector was used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

Number of distinct Claude Code sessions in which the connector was used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

Number of distinct Cowork sessions in which the connector was used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

Number of distinct Office Agent sessions in which the connector was used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

Number of artifacts created in Claude Code sessions: an artifact counts once, on the day a session first saves it. Counted from 2026-08-17; 0 on earlier days. Exact in date-range mode: a creation belongs to exactly one day, so the per-day counts never overlap and their sum over the window is the exact count of distinct creations in it.

Number of commits made via Claude Code

Number of distinct Claude Code sessions. On aggregated rows and in date-range mode: summed per-day distinct counts. A session essentially never spans a UTC day, so the sum is in practice the true distinct count.

Number of pull requests created via Claude Code

Number of distinct Claude Design projects created. Exact in date-range mode: a creation belongs to exactly one day, so the per-day counts never overlap and their sum over the window is the exact count of distinct creations in it.

Number of distinct Claude Design projects the user worked in. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

Number of distinct Claude Design sessions. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

Number of messages sent in Claude Design sessions

The provider's identifier for the caller: on aws, the IAM principal ARN (one role is one actor across its sessions); on gcp, the caller's IAM principal identifier as Google Cloud reports it, such as serviceAccount:<email>, user:<email>, or a principal://... URI.

The AWS account the organization is bound to.

The AWS-signed ARN of the IAM principal that made the requests.

The Azure subscription the organization is bound to.

The Google Cloud project the organization is bound to.

The federation issuer's URL.

Lines of code added

Lines of code removed

Number of MCP connector invocations

Number of distinct MCP connectors used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

Number of distinct Office Agent sessions. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

Number of distinct skills used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

Number of messages sent

Number of skill invocations

Number of distinct Claude Code sessions in which the plugin was invoked. Null on aggregated rows where a distinct count cannot be computed.

Number of distinct Cowork sessions in which the plugin was invoked. Null on aggregated rows where a distinct count cannot be computed.

Actor type. Always "user_actor".

True when the account has been deleted, or when the user is no longer a member of the organization or its associated organizations (for example, their membership was removed or they were deprovisioned via your identity provider). email_address stays populated for removed users and is null when the account has been deleted. name follows the rules described on that field. The user_id is still populated for reconciliation.

The user's current email address, including for users who are no longer members of the organization. Null when the account has been deleted and for system-minted service accounts.

The user's current full name. Null when the user has not set one. "Deleted User" when the account has been deleted, or when the user is no longer a member and the organization hides removed users' names.

Tagged user ID.

Number of delegations (handoffs to a specialized agent) in Claude Science sessions

Number of distinct Claude Science sessions. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

Number of messages sent in Claude Science sessions

Number of remote compute jobs launched from Claude Science sessions

Total number of skill invocations in Claude Science sessions

The number of web search requests made.

Tagged service account ID.

Same measure as chat_metrics.distinct_conversation_skill_used_count, for activity recorded while members had Chat and Cowork unified turned on. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

Same measure as cowork_metrics.distinct_session_skill_used_count, for activity recorded while members had Chat and Cowork unified turned on. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

Number of distinct conversations in which the skill was used. A skill counts as used only when it is explicitly activated — the model (or the user, via the skill's slash command) invokes it, reading its instructions into context as part of that activation. Skills that are merely installed or listed as available, or whose content reaches the context without an activation (preloaded, hook-injected, or read as a plain file), are not counted. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

Number of distinct Claude Code sessions in which the skill was used. A skill counts as used only when it is explicitly activated — the model (or the user, via the skill's slash command) invokes it, reading its instructions into context as part of that activation. Skills that are merely installed or listed as available, or whose content reaches the context without an activation (preloaded, hook-injected, or read as a plain file), are not counted. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

Number of distinct Cowork sessions in which the skill was used. A skill counts as used only when it is explicitly activated — the model (or the user, via the skill's slash command) invokes it, reading its instructions into context as part of that activation. Skills that are merely installed or listed as available, or whose content reaches the context without an activation (preloaded, hook-injected, or read as a plain file), are not counted. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

Number of distinct Office Agent sessions in which the skill was used. A skill counts as used only when it is explicitly activated — the model (or the user, via the skill's slash command) invokes it, reading its instructions into context as part of that activation. Skills that are merely installed or listed as available, or whose content reaches the context without an activation (preloaded, hook-injected, or read as a plain file), are not counted. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

Number of tool proposals accepted

Number of tool proposals rejected

Object type. Always user.

Tagged user identifier (e.g. user_...)

Email address of the user

Actor type. Always "user_actor".

True when the account has been deleted, or when the user is no longer a member of the organization or its associated organizations (for example, their membership was removed or they were deprovisioned via your identity provider). email_address stays populated for removed users and is null when the account has been deleted. name follows the rules described on that field. The user_id is still populated for reconciliation.

The user's email address, including for users who are no longer members of the organization or its associated organizations. Null when the account has been deleted (check deleted) and for system-minted service accounts, which have no person's mailbox behind them (check name).

The user's full name. Null when the user has not set a name. Returns "Deleted User" when the account itself has been deleted, or when the user is no longer a member of the organization or its associated organizations and the organization has chosen to hide the names of removed users. Otherwise, the name stays populated for removed users. Rows for system-minted service accounts render the service name (for example, "Claude Security" for usage by Anthropic's security-patching service) or null.

Tagged user ID.