분석

Models

beta_analytics_artifact_activity: object{ artifact_type, artifacts_created_count, distinct_user_count, 6 more }

Artifact-creation activity for one (artifact_type, is_shared) bucket on a given day.

Artifacts form a small finite cube — the canonical MIME type (8 values incl. other) crossed with shared-vs-private — so the response is the full set of non-empty buckets, not a ranked/paginated list. Claude Code and Cowork artifacts report under text/html and are counted from 2026-08-17 onward; earlier days contain claude.ai chat artifacts only. With group_by[]=product / user_id / rbac_group_id each row is further split by the flat group keys and counts are scoped to that cut.

beta_analytics_chat_cowork_unified_chat_metrics: object{ connectors_used_count, distinct_artifacts_created_count, distinct_connectors_used_count, 9 more }

Chat activity recorded while members had Chat and Cowork unified turned on.

beta_analytics_chat_cowork_unified_sessions_metrics: object{ action_count, artifacts_created_count, connectors_used_count, 14 more }

Cowork session activity recorded while members had Chat and Cowork unified turned on.

beta_analytics_chat_metrics: object{ connectors_used_count, distinct_artifacts_created_count, distinct_connectors_used_count, 9 more }

Claude.ai activity metrics for a single user on a given day.

beta_analytics_claude_code_metrics: object{ core_metrics, tool_actions }

Claude Code activity metrics for a single user on a given day.

beta_analytics_claude_tag_category: "dm" or "engaged" or "monitoring" or 2 more

"dm"

"engaged"

"monitoring"

"proactive"

"scheduled"

beta_analytics_connector_activity: object{ chat_metrics, claude_code_metrics, connector_name, 14 more }

Per-connector activity data for a given day.

beta_analytics_connector_chat_cowork_unified_chat_metrics: object{ distinct_conversation_connector_used_count }

A connector's use in chat conversations recorded while members had Chat and Cowork unified turned on.

distinct_conversation_connector_used_count: number

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.

beta_analytics_connector_chat_cowork_unified_sessions_metrics: object{ distinct_session_connector_used_count }

A connector's use in Cowork sessions recorded while members had Chat and Cowork unified turned on.

distinct_session_connector_used_count: number

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.

beta_analytics_connector_chat_metrics: object{ distinct_conversation_connector_used_count }

Claude.ai activity metrics for a single connector on a given day.

distinct_conversation_connector_used_count: number

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.

beta_analytics_connector_claude_code_metrics: object{ distinct_session_connector_used_count }

Claude Code activity metrics for a single connector on a given day.

distinct_session_connector_used_count: number

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.

beta_analytics_connector_cowork_metrics: object{ distinct_session_connector_used_count }

Cowork activity metrics for a single connector on a given day.

distinct_session_connector_used_count: number

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.

beta_analytics_connector_office_metrics: object{ excel, outlook, powerpoint, word }

Office Agent activity metrics for a single connector on a given day, broken out by Office product.

beta_analytics_connector_office_product_metrics: object{ distinct_session_connector_used_count }

Office Agent activity metrics for a single connector on a given day within one Office product.

distinct_session_connector_used_count: number

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.

beta_analytics_context_window: "0-200k" or "200k-1M"

"0-200k"

"200k-1M"

beta_analytics_core_code_metrics: object{ artifacts_created_count, commit_count, distinct_session_count, 2 more }

Core Claude Code activity metrics for a single user on a given day.

artifacts_created_count: number

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.

commit_count: number

Number of commits made via Claude Code

distinct_session_count: number

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.

lines_of_code: object{ added_count, removed_count }

Lines of code added and removed via Claude Code.

added_count: number

Lines of code added

removed_count: number

Lines of code removed

pull_request_count: number

Number of pull requests created via Claude Code

beta_analytics_cost_bucketed_result: object{ amount, claude_tag_category, claude_tag_user_id, 12 more }

beta_analytics_cost_report_time_bucket: object{ ending_at, results, starting_at }

beta_analytics_cost_type: "code_execution" or "tokens" or "web_search"

"code_execution"

"tokens"

"web_search"

beta_analytics_cost_users_item: object{ actor, amount, claude_tag_category, 15 more }

beta_analytics_cowork_metrics: object{ action_count, artifacts_created_count, connectors_used_count, 14 more }

Cowork activity metrics for a single user on a given day.

beta_analytics_design_metrics: object{ distinct_projects_created_count, distinct_projects_used_count, distinct_session_count, message_count }

Claude Design activity metrics for a single user on a given day.

distinct_projects_created_count: number

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.

distinct_projects_used_count: number

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.

distinct_session_count: number

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.

message_count: number

Number of messages sent in Claude Design sessions

beta_analytics_inference_geo_filter: "global" or "not_available" or "us"

"global"

"not_available"

"us"

beta_analytics_lines_of_code: object{ added_count, removed_count }

Lines of code added and removed via Claude Code.

added_count: number

Lines of code added

removed_count: number

Lines of code removed

beta_analytics_office_metrics: object{ excel, outlook, powerpoint, word }

Office Agent activity metrics for a single user on a given day, broken out by Office product.

beta_analytics_office_product_metrics: object{ connectors_used_count, distinct_connectors_used_count, distinct_session_count, 3 more }

Office Agent activity metrics for a single user on a given day within one Office product.

connectors_used_count: number

Number of MCP connector invocations

distinct_connectors_used_count: number

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.

distinct_session_count: number

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.

distinct_skills_used_count: number

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.

message_count: number

Number of messages sent

skills_used_count: number

Number of skill invocations

beta_analytics_plugin_activity: object{ claude_code_metrics, cowork_metrics, distinct_user_count, 9 more }

Per-plugin install + invocation activity for a given day.

With group_by[]=user_id / rbac_group_id / product (cowork, claude_code and chat_cowork_unified only on this endpoint) each row is one (plugin, user), (plugin, group), or (plugin, product) cut: the flat user_id / rbac_group_id / product keys carry the cut and the counts are scoped to it.

beta_analytics_plugin_claude_code_metrics: object{ distinct_session_plugin_used_count }

Claude Code activity metrics for a single plugin on a given day.

distinct_session_plugin_used_count: number

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

beta_analytics_plugin_cowork_metrics: object{ distinct_session_plugin_used_count }

Cowork activity metrics for a single plugin on a given day.

distinct_session_plugin_used_count: number

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

beta_analytics_product_filter: "chat" or "chat_cowork_unified" or "claude-tag" or 5 more

Publicly documented product surfaces. claude-tag is Claude Tag, the Claude product in Slack. chat_cowork_unified is Chat and Cowork unified, Cowork's features inside claude.ai chat: chat and Cowork usage by a member who has it turned on is reported under this value instead of chat or cowork. It is accepted as a filter only on deployments that offer Chat and Cowork unified.

"chat"

"chat_cowork_unified"

"claude-tag"

"claude_code"

"claude_design"

"claude_in_chrome"

"cowork"

"office_agent"

beta_analytics_project_activity: object{ distinct_user_count, message_count, project_id, 8 more }

Per-project activity data for a given day.

beta_analytics_science_metrics: object{ delegation_count, distinct_session_count, message_count, 2 more }

Claude Science activity metrics for a single user on a given day.

delegation_count: number

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

distinct_session_count: number

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.

message_count: number

Number of messages sent in Claude Science sessions

remote_compute_job_count: number

Number of remote compute jobs launched from Claude Science sessions

skills_used_count: number

Total number of skill invocations in Claude Science sessions

beta_analytics_server_tool_use: object{ web_search_requests }

web_search_requests: number

The number of web search requests made.

beta_analytics_single_day_activity_summary: object{ assigned_seat_count, cowork_daily_active_user_count, cowork_monthly_active_user_count, 29 more }

Per-day entry in the /summaries response.

beta_analytics_skill_activity: object{ chat_metrics, claude_code_metrics, cowork_metrics, 15 more }

Per-skill activity data for a given day.

beta_analytics_skill_chat_cowork_unified_chat_metrics: object{ distinct_conversation_skill_used_count }

A skill's use in chat conversations recorded while members had Chat and Cowork unified turned on.

distinct_conversation_skill_used_count: number

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.

beta_analytics_skill_chat_cowork_unified_sessions_metrics: object{ distinct_session_skill_used_count }

A skill's use in Cowork sessions recorded while members had Chat and Cowork unified turned on.

distinct_session_skill_used_count: number

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.

beta_analytics_skill_chat_metrics: object{ distinct_conversation_skill_used_count }

Claude.ai activity metrics for a single skill on a given day.

distinct_conversation_skill_used_count: number

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.

beta_analytics_skill_claude_code_metrics: object{ distinct_session_skill_used_count }

Claude Code activity metrics for a single skill on a given day.

distinct_session_skill_used_count: number

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.

beta_analytics_skill_cowork_metrics: object{ distinct_session_skill_used_count }

Cowork activity metrics for a single skill on a given day.

distinct_session_skill_used_count: number

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.

beta_analytics_skill_office_metrics: object{ excel, outlook, powerpoint, word }

Office Agent activity metrics for a single skill on a given day, broken out by Office product.

beta_analytics_skill_office_product_metrics: object{ distinct_session_skill_used_count }

Office Agent activity metrics for a single skill on a given day within one Office product.

distinct_session_skill_used_count: number

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.

beta_analytics_token_type: "cache_creation.ephemeral_1h_input_tokens" or "cache_creation.ephemeral_5m_input_tokens" or "cache_read_input_tokens" or 2 more

"cache_creation.ephemeral_1h_input_tokens"

"cache_creation.ephemeral_5m_input_tokens"

"cache_read_input_tokens"

"output_tokens"

"uncached_input_tokens"

beta_analytics_tool_action_counts: object{ accepted_count, rejected_count }

Accepted/rejected counts for a single Claude Code tool type.

accepted_count: number

Number of tool proposals accepted

rejected_count: number

Number of tool proposals rejected

beta_analytics_tool_actions: object{ edit_tool, multi_edit_tool, notebook_edit_tool, write_tool }

Per-tool accepted/rejected counts for Claude Code file modification tools.

beta_analytics_usage_bucketed_result: object{ cache_creation, cache_read_input_tokens, claude_tag_category, 12 more }

beta_analytics_usage_report_time_bucket: object{ ending_at, results, starting_at }

beta_analytics_usage_users_item: object{ actor, cache_creation, cache_read_input_tokens, 16 more }

beta_analytics_user: object{ type: "user", id, email_address }

A user in the organization, identified by tagged id and email address.

type: "user"

Object type. Always user.

id: string

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

email_address: string

Email address of the user

beta_analytics_user_activity: object{ chat_metrics, claude_code_metrics, cowork_metrics, 10 more }

Per-user activity data for a given day.

beta_analytics_user_actor: object{ type: "user_actor", deleted, email_address, 2 more }

type: "user_actor"

Actor type. Always "user_actor".

deleted: boolean

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.

email_address: string

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).

name: string

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.

user_id: string

Tagged user ID.