# Clarifeye

## Docs

- [What is Clarifeye?](https://docs.clarifeye.ai/guides/what-is-clarifeye.md): Clarifeye captures your organization's expertise and turns it into knowledge that AI can use faithfully.
- [Quickstart](https://docs.clarifeye.ai/guides/quickstart.md): Go from an empty knowledge store to one your team can use through an AI client.
- [Core concepts](https://docs.clarifeye.ai/guides/core-concepts.md): The handful of ideas that run through everything else in Clarifeye.
- [Create your knowledge store](https://docs.clarifeye.ai/guides/create-knowledge-store.md): Create your first knowledge store through a guided conversation with Clara.
- [Build & Improve](https://docs.clarifeye.ai/guides/build-improve.md): Capture knowledge from your experts and keep it accurate over time.
- [Knowledge](https://docs.clarifeye.ai/guides/knowledge.md): The consolidated artifacts and the sources behind them.
- [Use](https://docs.clarifeye.ai/guides/use.md): Put your knowledge store to work to produce a real output.
- [External MCPs](https://docs.clarifeye.ai/guides/external-mcps.md): Connect external MCP servers as tools Clara can call.
- [SharePoint](https://docs.clarifeye.ai/guides/sharepoint.md): Connect a SharePoint site as a source.
- [Connect to AI clients](https://docs.clarifeye.ai/guides/mcp.md): Bring your knowledge stores into Claude, ChatGPT, Copilot, or any custom client.
- [MCP authentication](https://docs.clarifeye.ai/guides/mcp-authentication.md): Authenticate to the Clarifeye MCP server using a user token or OAuth.
- [MCP tools](https://docs.clarifeye.ai/guides/mcp-tools.md): The tools the Clarifeye MCP server exposes to AI clients.
- [Claude](https://docs.clarifeye.ai/guides/mcp-claude.md): Connect Clarifeye to Claude.ai using MCP connectors and skills
- [ChatGPT](https://docs.clarifeye.ai/guides/mcp-chatgpt.md): Connect Clarifeye to ChatGPT using MCP apps and skills
- [Microsoft Copilot](https://docs.clarifeye.ai/guides/mcp-copilot.md): Connect Clarifeye to Microsoft Copilot using MCP tools
- [Other clients](https://docs.clarifeye.ai/guides/mcp-generic.md): Connect Clarifeye to any AI assistant that supports MCP.
- [Send signals from Slack & Teams](https://docs.clarifeye.ai/guides/signals-slack.md): Send signals to Clarifeye from Slack or Microsoft Teams by calling the API from your own app.
- [Organization settings](https://docs.clarifeye.ai/guides/organization-settings.md): The organization-level layer that shapes every knowledge store beneath it.
- [User management](https://docs.clarifeye.ai/guides/user-management.md): Profiles, permissions, and how to invite users to a knowledge store.
- [Single Sign-On (SSO)](https://docs.clarifeye.ai/guides/sso.md): Set up SSO with OpenID Connect (OIDC) or SAML for Clarifeye
- [Compliance & Certifications](https://docs.clarifeye.ai/guides/compliance.md): Our security standards and compliance certifications
- [Connect to a Light LLM Gateway](https://docs.clarifeye.ai/guides/llm-gateway.md): Route Clarifeye's LLM and agentic calls through your own LiteLLM gateway, one model at a time.
- [Other Security Settings](https://docs.clarifeye.ai/guides/other-security.md): Other security settings in Clarifeye
- [List project users](https://docs.clarifeye.ai/api-reference/users/list-project-users.md): Retrieve all users with access to a project.
- [Remove user by email](https://docs.clarifeye.ai/api-reference/users/remove-user-by-email.md): Remove a user from the project using their email address. Users cannot remove themselves.
- [Update user permissions](https://docs.clarifeye.ai/api-reference/users/update-user-permissions.md): Update a user's permissions on the project.
- [List invitations](https://docs.clarifeye.ai/api-reference/invitations/list-invitations.md): Retrieve all invitations for a project with optional filtering by status.
- [Invite user to project](https://docs.clarifeye.ai/api-reference/invitations/invite-user-to-project.md): Invite a user to join the project. - For new users (not registered): Creates a pending invite and sends an email. - For existing users: Automatically accepts the invite and sends a notification.
- [Cancel invitation](https://docs.clarifeye.ai/api-reference/invitations/cancel-invitation.md): Cancel a pending invitation. Only pending invitations can be cancelled.
- [Get document indexing status](https://docs.clarifeye.ai/api-reference/documents/get-document-indexing-status.md): Returns the indexing status for each `(document, extractor node)` pair in the project. Callers poll this endpoint until documents reach `active` (queryable by AI) or `deleted`.
- [Bulk upload documents](https://docs.clarifeye.ai/api-reference/documents/bulk-upload-documents.md): Upload multiple documents at once. Optionally skip the automatic parsing pipeline.
- [Delete document](https://docs.clarifeye.ai/api-reference/documents/delete-document.md): Delete a document from the project. Deletion is always asynchronous.
- [List documents without file data](https://docs.clarifeye.ai/api-reference/documents/list-documents-without-file-data.md): Retrieve document metadata without file URLs for faster response times.
- [Filter documents by tag values](https://docs.clarifeye.ai/api-reference/documents/filter-documents-by-tag-values.md): Retrieve documents that match one or more tag values (case-insensitive). Pass tag values as a JSON array to avoid delimiter issues with values containing commas.
- [Filter documents by metadata values](https://docs.clarifeye.ai/api-reference/documents/filter-documents-by-metadata-values.md): Retrieve documents whose metadata contains one or more of the given values (case-insensitive, OR logic).
- [List signals](https://docs.clarifeye.ai/api-reference/signals/list-signals.md): Retrieve all signals for a project with optional filtering.
- [Submit a signal](https://docs.clarifeye.ai/api-reference/signals/submit-a-signal.md): Submit a signal about the project's content: the signal text itself, plus optional `context.additional_details` with extra context for the reviewer. The signal shows up in the review UI for domain experts.
- [Update signal status](https://docs.clarifeye.ai/api-reference/signals/update-signal-status.md): Mark a signal as reviewed or update other fields.
- [List tools](https://docs.clarifeye.ai/api-reference/tools/list-tools.md): List all tools available to the project, including tools owned by the project (`category: local`) and tools imported from other projects (`category: imported`).
- [Get tool parameters schema](https://docs.clarifeye.ai/api-reference/tools/get-tool-parameters-schema.md): Return the JSON schema describing the parameters accepted by [`runTool`](#operation/runTool) for this tool.
- [Run a tool](https://docs.clarifeye.ai/api-reference/tools/run-a-tool.md): Execute a configured tool with provided parameters.
- [List interviews](https://docs.clarifeye.ai/api-reference/interviews/list-interviews.md): Retrieve interviews for a project.
- [Create and assign interviews](https://docs.clarifeye.ai/api-reference/interviews/create-and-assign-interviews.md): Create and assign one interview per assignee. **Admin only.**
- [Retrieve interview content](https://docs.clarifeye.ai/api-reference/interviews/retrieve-interview-content.md): Retrieve a single interview with its full content, including the complete `chat_history` transcript and `chat_memory`.
- [Import an external interview transcript](https://docs.clarifeye.ai/api-reference/interviews/import-an-external-interview-transcript.md): Import the transcript of an interview recorded outside the platform (e.g. a Granola/Teams/Zoom export). **Admin only.**
- [List interview campaigns](https://docs.clarifeye.ai/api-reference/interviews/list-interview-campaigns.md): List the project's interview campaigns (named groups of interviews, e.g. a workshop wave or rollout round), newest first. Any project member can read.
- [Get conversation](https://docs.clarifeye.ai/api-reference/conversations/get-conversation.md): Retrieve a conversation with its complete chat history.
- [Back office concepts](https://docs.clarifeye.ai/backoffice/concepts.md): The extraction flow, extractors, agent settings, and tools — for technical users who customize Clarifeye.
- [Pre-create (or re-activate) an org user](https://docs.clarifeye.ai/backoffice/user-provisioning/pre-create-or-re-activate-an-org-user.md): Pre-creates a user bound to this organization, with a verified primary email so a later SSO login links to it automatically. Idempotent: re-provisioning an existing member is a no-op (role/state unchanged). The email's domain must be in the org's `allowed_provisioning_domains`. The API key must belo…
- [Remove an org user's membership](https://docs.clarifeye.ai/backoffice/user-provisioning/remove-an-org-users-membership.md): Removes the user's membership in this organization. If the user has no remaining memberships they are deactivated (blocking SSO login); otherwise their active organization is re-pointed. Returns `deprovisioned: false` if no such user. The API key must belong to the organization in the path.
- [Read the org's allowed provisioning domains (superuser only)](https://docs.clarifeye.ai/backoffice/user-provisioning/read-the-orgs-allowed-provisioning-domains-superuser-only.md)
- [Set the org's allowed provisioning domains (superuser only)](https://docs.clarifeye.ai/backoffice/user-provisioning/set-the-orgs-allowed-provisioning-domains-superuser-only.md)
- [List API keys (superuser → all; org admin → own org's keys)](https://docs.clarifeye.ai/backoffice/organization-api-keys/list-api-keys-superuser-→-all;-org-admin-→-own-orgs-keys.md)
- [Mint an API key (superuser only)](https://docs.clarifeye.ai/backoffice/organization-api-keys/mint-an-api-key-superuser-only.md): The full `api_key` is returned ONCE in this response.
- [Retrieve API key metadata (superuser or org admin)](https://docs.clarifeye.ai/backoffice/organization-api-keys/retrieve-api-key-metadata-superuser-or-org-admin.md)
- [Delete an API key (superuser only)](https://docs.clarifeye.ai/backoffice/organization-api-keys/delete-an-api-key-superuser-only.md): Permanently deletes the key; it immediately stops authenticating.
- [Download the full secret (superuser or org admin)](https://docs.clarifeye.ai/backoffice/organization-api-keys/download-the-full-secret-superuser-or-org-admin.md)
- [List a knowledge store's external MCP servers](https://docs.clarifeye.ai/backoffice/external-mcp/list-a-knowledge-stores-external-mcp-servers.md): Project members can read; only project admins can create/edit.
- [Register an external MCP server (admin)](https://docs.clarifeye.ai/backoffice/external-mcp/register-an-external-mcp-server-admin.md): Creates a server and synchronously syncs its tool catalog (all tools start disabled). ``url`` and ``auth_mode`` are immutable after creation. The ``oauth_client_secret`` is write-only. API keys are per-user (set on the account endpoint), never on the server.
- [Remove an external MCP server (admin)](https://docs.clarifeye.ai/backoffice/external-mcp/remove-an-external-mcp-server-admin.md)
- [Update an external MCP server (admin)](https://docs.clarifeye.ai/backoffice/external-mcp/update-an-external-mcp-server-admin.md): Edit name, enable/disable, tool allowlist, or rotate the OAuth client secret. ``url`` and ``auth_mode`` are immutable.
- [Re-sync an MCP server's tool catalog (admin)](https://docs.clarifeye.ai/backoffice/external-mcp/re-sync-an-mcp-servers-tool-catalog-admin.md): Re-fetches the server's tools using the admin's own credential (OAuth) or the shared API key. Newly discovered tools start disabled; removed tools drop out of the allowlist. Rate limited.
- [Current user's connection status per enabled server](https://docs.clarifeye.ai/backoffice/external-mcp/current-users-connection-status-per-enabled-server.md): Drives the connect banner and empty-state connector prompt. Separate from the job-execution poll path.
- [List my external MCP connections](https://docs.clarifeye.ai/backoffice/external-mcp/list-my-external-mcp-connections.md): The current user's OAuth connections to external MCP servers, one per distinct server URL, grouped across all knowledge stores the user belongs to. Never returns tokens or client secrets.
- [Begin an external MCP OAuth connection](https://docs.clarifeye.ai/backoffice/external-mcp/begin-an-external-mcp-oauth-connection.md): Starts the OAuth authorization-code flow for an enabled OAuth MCP server the user can access. Returns the authorization URL for the frontend to open in a popup. Rate limited.
- [Re-authorize an existing MCP connection](https://docs.clarifeye.ai/backoffice/external-mcp/re-authorize-an-existing-mcp-connection.md)
- [Set the current user's API key for an api_key MCP server](https://docs.clarifeye.ai/backoffice/external-mcp/set-the-current-users-api-key-for-an-api_key-mcp-server.md): Stores the user's own API key for an enabled api_key server in one of their knowledge stores (encrypted at rest) and pushes it to their vault. Credentials are per-user; there is no shared store-level key.
- [Revoke an external MCP connection](https://docs.clarifeye.ai/backoffice/external-mcp/revoke-an-external-mcp-connection.md): Best-effort remote token revocation, removes the Anthropic vault credential, and marks the connection revoked.
- [List project users](https://docs.clarifeye.ai/backoffice/users/list-project-users.md): Retrieve all users with access to a project.
- [Remove user by email](https://docs.clarifeye.ai/backoffice/users/remove-user-by-email.md): Remove a user from the project using their email address. Users cannot remove themselves.
- [Update user permissions](https://docs.clarifeye.ai/backoffice/users/update-user-permissions.md): Update a user's permissions on the project.
- [List invitations](https://docs.clarifeye.ai/backoffice/invitations/list-invitations.md): Retrieve all invitations for a project with optional filtering by status.
- [Invite user to project](https://docs.clarifeye.ai/backoffice/invitations/invite-user-to-project.md): Invite a user to join the project. - For new users (not registered): Creates a pending invite and sends an email. - For existing users: Automatically accepts the invite and sends a notification.
- [Cancel invitation](https://docs.clarifeye.ai/backoffice/invitations/cancel-invitation.md): Cancel a pending invitation. Only pending invitations can be cancelled.
- [Bulk upload documents](https://docs.clarifeye.ai/backoffice/documents/bulk-upload-documents.md): Upload multiple documents at once. Optionally skip the automatic parsing pipeline.
- [Move a document to a collection](https://docs.clarifeye.ai/backoffice/documents/move-a-document-to-a-collection.md): Move a document into a collection, or out to "Default". Sets the `collection` foreign key and swaps the mirrored `["tag", slug]` pair so retrieval/extraction filters follow the move. Requires project admin permission.
- [Move multiple documents to a collection](https://docs.clarifeye.ai/backoffice/documents/move-multiple-documents-to-a-collection.md): Move up to 200 active documents into a collection, or out to "Default", in one request. Sets the `collection` foreign key and swaps the mirrored `["tag", slug]` pair on each document so retrieval/extraction filters follow the move. Requires project admin permission.
- [Delete document](https://docs.clarifeye.ai/backoffice/documents/delete-document.md): Delete a document from the project. Deletion is performed asynchronously - the document is marked as "deleting" and removed in the background.
- [List documents](https://docs.clarifeye.ai/backoffice/documents/list-documents.md): List a project's documents (paginated). Supports text search, status filtering, and filtering by collection.
- [List document collections](https://docs.clarifeye.ai/backoffice/documents/list-document-collections.md): List the project's document collections. Available to all project members.
- [Create a document collection](https://docs.clarifeye.ai/backoffice/documents/create-a-document-collection.md): Create a collection. The `slug` is derived server-side from `name` (deduplicated per project) and cannot be set by the client. Requires admin permissions.
- [Retrieve a document collection](https://docs.clarifeye.ai/backoffice/documents/retrieve-a-document-collection.md)
- [Delete a document collection](https://docs.clarifeye.ai/backoffice/documents/delete-a-document-collection.md): Delete the collection row. Linked documents keep their metadata and fall back to the virtual "Default" bucket. Requires admin permissions.
- [Rename a document collection](https://docs.clarifeye.ai/backoffice/documents/rename-a-document-collection.md): Update the collection's `name`. The `slug` is immutable. Requires admin permissions.
- [List documents without file data](https://docs.clarifeye.ai/backoffice/documents/list-documents-without-file-data.md): Retrieve document metadata without file URLs for faster response times.
- [Filter documents by tag values](https://docs.clarifeye.ai/backoffice/documents/filter-documents-by-tag-values.md): Retrieve documents that match one or more tag values (case-insensitive). Pass tag values as a JSON array to avoid delimiter issues with values containing commas.
- [Filter documents by metadata values](https://docs.clarifeye.ai/backoffice/documents/filter-documents-by-metadata-values.md): Retrieve documents whose metadata contains one or more of the given values (case-insensitive, OR logic).
- [List available document tags](https://docs.clarifeye.ai/backoffice/documents/list-available-document-tags.md): Retrieve all available document tag names and their possible values for the project.
- [List available document metadata](https://docs.clarifeye.ai/backoffice/documents/list-available-document-metadata.md): Retrieve all metadata keys and their distinct values across all active documents in the project.
- [Get document tags grouped by document](https://docs.clarifeye.ai/backoffice/documents/get-document-tags-grouped-by-document.md): Retrieve all document tags for the project, grouped by document ID. Optionally filter by specific document IDs.
- [Add metadata to a document](https://docs.clarifeye.ai/backoffice/documents/add-metadata-to-a-document.md): Add metadata to a document. Accepts **either** a single `{key, value}` pair **or** a list of `{key, value}` pairs in one request. Each pair is appended to the document's existing metadata list.
- [Remove a specific metadata pair](https://docs.clarifeye.ai/backoffice/documents/remove-a-specific-metadata-pair.md): Remove a specific key-value pair from a document's metadata. Both key and value must match exactly for the pair to be removed.
- [Remove all metadata pairs for a key](https://docs.clarifeye.ai/backoffice/documents/remove-all-metadata-pairs-for-a-key.md): Remove all metadata pairs matching the given key from a document, regardless of their values.
- [Get metadata values for a key](https://docs.clarifeye.ai/backoffice/documents/get-metadata-values-for-a-key.md): Retrieve all values associated with a given metadata key on a document.
- [Home dashboard summary](https://docs.clarifeye.ai/backoffice/projects/home-dashboard-summary.md): Everything the Standard-interface Home dashboard needs in one call: document count and last-added timestamp, plus the caller's open (pending or in-progress) interviews. For project admins the response additionally includes the team's pending interviews and the count of feedbacks awaiting review; the…
- [List knowledge changelog entries](https://docs.clarifeye.ai/backoffice/projects/list-knowledge-changelog-entries.md): List the project's knowledge changelog entries, most recent first. Each entry records a change to the project's knowledge (artifact edits, API ontology/playbook changes, document uploads/syncs). Read-only. Admin-only: the feed aggregates edits by all project members, so it requires CAN_PERFORM_ADMIN…
- [List knowledge artifact catalog](https://docs.clarifeye.ai/backoffice/projects/list-knowledge-artifact-catalog.md): Catalog overview for a knowledge store: `cohesion_guide`, `document_count` (number of active documents in the library), plus `artifacts[]` (one row per in-scope artifact with slug, title, semantic_type, technical_type, group,  purpose, and either full LIST `content` or a LIST `content_overview` summ…
- [Get warehouse tags and object schema](https://docs.clarifeye.ai/backoffice/projects/get-warehouse-tags-and-object-schema.md): Returns markdown sections `tag_hierarchies`, `document_tags`, and `knowledge_graph_objects` for retrieval filtering.
- [Read or edit a markdown catalog artifact](https://docs.clarifeye.ai/backoffice/projects/read-or-edit-a-markdown-catalog-artifact.md): Invoke the markdown artifact tool. Body must include `slug` (in-scope markdown artifact) plus tool kwargs (`action=get|edit`, …). Reads require view permission; writes require admin.
- [Read or edit a playbook_list catalog artifact](https://docs.clarifeye.ai/backoffice/projects/read-or-edit-a-playbook_list-catalog-artifact.md): Invoke the playbook_list artifact tool. Body must include `slug` plus tool kwargs (`action=list|get`, `identifier`, `changes`, …). Reads require view permission; writes require admin.
- [Read or edit a mental_map catalog artifact](https://docs.clarifeye.ai/backoffice/projects/read-or-edit-a-mental_map-catalog-artifact.md): Invoke the mental_map artifact tool. Body must include `slug` plus tool kwargs (`action=get`, `changes`, …). Reads require view permission; writes require admin.
- [Read or edit a design_template_list catalog artifact](https://docs.clarifeye.ai/backoffice/projects/read-or-edit-a-design_template_list-catalog-artifact.md): Invoke the design_template_list artifact tool. Body must include `slug` plus tool kwargs (`action=list|get|upsert|delete`, …). Reads require view permission; writes require admin.
- [List agent settings](https://docs.clarifeye.ai/backoffice/agent-settings/list-agent-settings.md): Retrieve all agent settings (AI agent configurations) for a project. Results are ordered by most recently updated first.
- [List conversations](https://docs.clarifeye.ai/backoffice/conversations/list-conversations.md): Retrieve all conversations for a project with optional filtering.
- [Create conversation](https://docs.clarifeye.ai/backoffice/conversations/create-conversation.md): Create a new AI-powered conversation.
- [Get conversation](https://docs.clarifeye.ai/backoffice/conversations/get-conversation.md): Retrieve a conversation with its complete chat history.
- [Archive conversation](https://docs.clarifeye.ai/backoffice/conversations/archive-conversation.md): Soft-archive a conversation. The conversation is hidden from default list/get endpoints but is preserved in the database along with all linked feedback.
- [Unarchive conversation](https://docs.clarifeye.ai/backoffice/conversations/unarchive-conversation.md): Restore a previously archived conversation back to active status.
- [Permanently delete conversation](https://docs.clarifeye.ai/backoffice/conversations/permanently-delete-conversation.md): Permanently delete an archived conversation and all its associated feedbacks. This action is irreversible.
- [Send message (async)](https://docs.clarifeye.ai/backoffice/conversations/send-message-async.md): Enqueue a chat turn and return `202 Accepted`. The turn runs in a background Celery task; poll the `poll` endpoint for progress and the final result. This replaces the former SSE `send_message_stream` endpoint.
- [Poll turn status](https://docs.clarifeye.ai/backoffice/conversations/poll-turn-status.md): Return the in-flight turn state for a conversation: the current `turn_status`, the accumulated message-level `turn_events` buffer, and `updated_at`. Clients poll this every few seconds after `send_message` returns `202` and re-render from the returned events. A `RUNNING` turn whose `updated_at` has…
- [Get all conversation tags](https://docs.clarifeye.ai/backoffice/conversations/get-all-conversation-tags.md): Retrieve all unique tags used across conversations in the project.
- [Share conversation](https://docs.clarifeye.ai/backoffice/conversations/share-conversation.md): Share a conversation with all workspace members.
- [Unshare conversation](https://docs.clarifeye.ai/backoffice/conversations/unshare-conversation.md): Remove sharing from a conversation.
- [Retrieve conversation feedback](https://docs.clarifeye.ai/backoffice/conversations/retrieve-conversation-feedback.md): List all feedback (including text content) attached to a conversation.
- [List interviews](https://docs.clarifeye.ai/backoffice/interviews/list-interviews.md): Retrieve interviews for a project.
- [Create and assign interviews](https://docs.clarifeye.ai/backoffice/interviews/create-and-assign-interviews.md): Create and assign one interview per assignee. **Admin only.**
- [List assignable users](https://docs.clarifeye.ai/backoffice/interviews/list-assignable-users.md): List project members who can be assigned an interview (tech/contributor profiles and pending tech/contributor invites), flagging admins. **Admin only.**
- [Stop automatic reminders](https://docs.clarifeye.ai/backoffice/interviews/stop-automatic-reminders.md): Permanently stop automatic reminder emails for one interview. **Admin or assigner only.** Manual reminders stay available; reminders also stop on completion or deletion. Returns 400 when the interview has no reminder schedule.
- [Send a scheduled invitation now](https://docs.clarifeye.ai/backoffice/interviews/send-a-scheduled-invitation-now.md): Send a scheduled-but-unsent interview invitation immediately, skipping the remaining wait on `scheduled_send_at`, and start the reminder clock. **Admin or assigner only.** Returns 400 when the interview is not an interview, has already been started, or its invitation was already sent.
- [Retrieve interview content](https://docs.clarifeye.ai/backoffice/interviews/retrieve-interview-content.md): Retrieve a single interview with its full content, including the complete `chat_history` transcript and `chat_memory`.
- [Update an interview](https://docs.clarifeye.ai/backoffice/interviews/update-an-interview.md): Partially update an interview's writable fields — most usefully `name` (rename) and `campaign_id` (move the interview to another campaign of the project, or null to remove it from its campaign, so past interviews can be re-bucketed retroactively). Lifecycle and transcript fields are read-only.
- [Duplicate an interview as a draft](https://docs.clarifeye.ai/backoffice/interviews/duplicate-an-interview-as-a-draft.md): Duplicate one interview into a fresh, unsent draft. **Admin only.**
- [Download all interview files as a zip](https://docs.clarifeye.ai/backoffice/interviews/download-all-interview-files-as-a-zip.md): Download every file uploaded during the interview as a single zip archive (entries ordered by upload time; duplicate filenames are suffixed).
- [Import an external interview transcript](https://docs.clarifeye.ai/backoffice/interviews/import-an-external-interview-transcript.md): Import the transcript of an interview recorded outside the platform (e.g. a Granola/Teams/Zoom export). **Admin only.**
- [Retry a failed transcript import](https://docs.clarifeye.ai/backoffice/interviews/retry-a-failed-transcript-import.md): Re-run the async parse of an imported transcript. **Admin only.**
- [List interview drafts](https://docs.clarifeye.ai/backoffice/interviews/list-interview-drafts.md): List the project's saved-but-unsent interview drafts, most recently updated first. **Admin only** (like everything pre-send).
- [Create an interview draft](https://docs.clarifeye.ai/backoffice/interviews/create-an-interview-draft.md): Save a draft of an interview assignment. **Admin only.**
- [Retrieve an interview draft](https://docs.clarifeye.ai/backoffice/interviews/retrieve-an-interview-draft.md): Retrieve one saved draft. **Admin only.**
- [Delete an interview draft](https://docs.clarifeye.ai/backoffice/interviews/delete-an-interview-draft.md): Discard a saved draft. **Admin only.** Nothing was sent, so deleting a draft has no side effects. Sending a draft (assign with `draft_id`) deletes it automatically.
- [Update an interview draft](https://docs.clarifeye.ai/backoffice/interviews/update-an-interview-draft.md): Partially update a saved draft. **Admin only.** Changing the topic regenerates the draft's `name`; clearing it clears the name.
- [Duplicate an interview draft](https://docs.clarifeye.ai/backoffice/interviews/duplicate-an-interview-draft.md): Duplicate a saved draft verbatim into a new draft. **Admin only.**
- [List interview campaigns](https://docs.clarifeye.ai/backoffice/interviews/list-interview-campaigns.md): List the project's interview campaigns with their progress aggregates, most recently created first. **Admin only** — the response covers every interview in each campaign, including ones the caller cannot otherwise see.
- [Retrieve an interview campaign](https://docs.clarifeye.ai/backoffice/interviews/retrieve-an-interview-campaign.md): Retrieve one campaign with its progress aggregates. **Admin only.**
- [Rename an interview campaign](https://docs.clarifeye.ai/backoffice/interviews/rename-an-interview-campaign.md): Rename a campaign. **Admin only.** `name` is the only writable field — campaigns cannot be created or deleted through the API. Names are unique per project, case-insensitively; a clash returns 400.
- [Remind every unfinished interview in a campaign](https://docs.clarifeye.ai/backoffice/interviews/remind-every-unfinished-interview-in-a-campaign.md): Send a reminder (or a "finish your interview" nudge for in-progress ones) to the assignee of each unfinished interview in the campaign. **Admin only.**
- [List feedback](https://docs.clarifeye.ai/backoffice/feedback/list-feedback.md): Retrieve all feedback for a project with optional filtering.
- [Submit feedback](https://docs.clarifeye.ai/backoffice/feedback/submit-feedback.md): Submit feedback. The simplest form is direct feedback about content: just the feedback text and optional `context.additional_details`, with no conversation attached. Feedback can also be linked to a playground conversation message, or submitted by an agent through MCP.
- [Delete feedback](https://docs.clarifeye.ai/backoffice/feedback/delete-feedback.md): Remove feedback.
- [Update feedback status](https://docs.clarifeye.ai/backoffice/feedback/update-feedback-status.md): Mark feedback as reviewed or update other fields.
- [Get feedbacks grouped by conversation](https://docs.clarifeye.ai/backoffice/feedback/get-feedbacks-grouped-by-conversation.md): Retrieve feedbacks grouped by their associated playground conversation with unified pagination and sorting.
- [Mark all feedbacks in a conversation as reviewed](https://docs.clarifeye.ai/backoffice/feedback/mark-all-feedbacks-in-a-conversation-as-reviewed.md): Update the status of all feedbacks associated with a specific conversation to "reviewed".
- [Get feedback counts by status](https://docs.clarifeye.ai/backoffice/feedback/get-feedback-counts-by-status.md): Retrieve comprehensive counts of feedbacks split by status, conversation grouping, and ungrouped feedbacks.
- [List tools](https://docs.clarifeye.ai/backoffice/tools/list-tools.md): List all tools available to the project, including tools owned by the project (`category: local`) and tools imported from other projects (`category: imported`).
- [Get tool parameters schema](https://docs.clarifeye.ai/backoffice/tools/get-tool-parameters-schema.md): Return the JSON schema describing the parameters accepted by [`runTool`](#operation/runTool) for this tool.
- [Run a tool](https://docs.clarifeye.ai/backoffice/tools/run-a-tool.md): Execute a configured tool with provided parameters.
- [Read extractor output rows](https://docs.clarifeye.ai/backoffice/tables/read-extractor-output-rows.md): Read-only retrieval of rows produced by a specific `ExtractorVersion`, joining the warehouse table with `HydrationComputation` records.
- [List project notifications](https://docs.clarifeye.ai/backoffice/notifications/list-project-notifications.md): List notifications for the effective user (authenticated user or impersonated user).
- [Retrieve a notification](https://docs.clarifeye.ai/backoffice/notifications/retrieve-a-notification.md): Retrieve details of a single notification for the effective user.
- [Delete a notification](https://docs.clarifeye.ai/backoffice/notifications/delete-a-notification.md): Delete a single notification for the effective user.
- [Mark notification as read](https://docs.clarifeye.ai/backoffice/notifications/mark-notification-as-read.md): Mark a single notification as read for the effective user.
- [Mark notification as unread](https://docs.clarifeye.ai/backoffice/notifications/mark-notification-as-unread.md): Mark a single notification as unread for the effective user.
- [Mark all notifications as read](https://docs.clarifeye.ai/backoffice/notifications/mark-all-notifications-as-read.md): Mark all unread project notifications as read for the effective user.
- [Delete all read notifications](https://docs.clarifeye.ai/backoffice/notifications/delete-all-read-notifications.md): Delete all read project notifications for the effective user.
- [List extraction flows](https://docs.clarifeye.ai/backoffice/extraction-flows/list-extraction-flows.md): List all extraction flows for the project, ordered by most recently updated.
- [Update an extraction flow](https://docs.clarifeye.ai/backoffice/extraction-flows/update-an-extraction-flow.md): Partially update an extraction flow. Common uses are switching the **publish mode** and editing the **DAG** (adding, modifying or removing nodes).
- [Run an extraction flow](https://docs.clarifeye.ai/backoffice/extraction-flows/run-an-extraction-flow.md): Queue a pipeline run that executes the flow's DAG across the given documents (or all project documents if `document_ids` is omitted).
- [Get extraction flow statistics](https://docs.clarifeye.ai/backoffice/extraction-flows/get-extraction-flow-statistics.md): Dry-run cache simulation of the flow — returns, per DAG node, how many inputs would be reused from cache vs. recomputed, without actually executing any extraction. Useful to preview the cost/impact of a run.
- [Publish an extraction flow](https://docs.clarifeye.ai/backoffice/extraction-flows/publish-an-extraction-flow.md): Queue a pipeline run that publishes previously-extracted data to the downstream indexes without re-running extraction.
- [List pipeline runs](https://docs.clarifeye.ai/backoffice/pipeline-runs/list-pipeline-runs.md): List all pipeline runs in the project, ordered by creation date (most recent first). Use this to discover the `id` of a run returned by an extraction flow `run-sync` / `publish` call, or to monitor recent activity.
- [Get pipeline run details and status](https://docs.clarifeye.ai/backoffice/pipeline-runs/get-pipeline-run-details-and-status.md): Retrieve the full details of a single pipeline run, including its current `status`, the list of executed steps with their per-step status, and the aggregated `raw_logs` produced during execution.
- [Abort a pipeline run](https://docs.clarifeye.ai/backoffice/pipeline-runs/abort-a-pipeline-run.md): Cancel a pipeline run that is `pending` or `running`. The run and any of its non-terminal steps transition to `aborted`.
- [List object extractors](https://docs.clarifeye.ai/backoffice/object-extractors/list-object-extractors.md): List all `ObjectExtractor` rows in the project, newest first.
- [Create object extractor](https://docs.clarifeye.ai/backoffice/object-extractors/create-object-extractor.md): Create an `ObjectExtractor`. A first `ObjectExtractorVersion` is created automatically and marked as default. Pass `import_mode: true` to skip auto-version creation (bulk imports only).
- [Retrieve object extractor](https://docs.clarifeye.ai/backoffice/object-extractors/retrieve-object-extractor.md)
- [Delete object extractor](https://docs.clarifeye.ai/backoffice/object-extractors/delete-object-extractor.md): Delete the `ObjectExtractor`. Related warehouse tables (`extracted_objects_table`, `alerts_table`) are cleaned up on cascade.
- [Update object extractor (auto-creates new version)](https://docs.clarifeye.ai/backoffice/object-extractors/update-object-extractor-auto-creates-new-version.md): Partial update of an `ObjectExtractor`. If any **version-bearing** field differs from the latest version, a new `ObjectExtractorVersion` row is created automatically. Version-bearing fields: `extractable_pydantic_class`, `extraction_prompt`, `llm_model`, `add_anchoring_object`, `filtered_on_block_ty…
- [List tag extractors](https://docs.clarifeye.ai/backoffice/tag-extractors/list-tag-extractors.md)
- [Create tag extractor](https://docs.clarifeye.ai/backoffice/tag-extractors/create-tag-extractor.md): Create a `TagExtractor`. A first `TagExtractorVersion` is created automatically and marked as default.
- [Retrieve tag extractor](https://docs.clarifeye.ai/backoffice/tag-extractors/retrieve-tag-extractor.md)
- [Delete tag extractor](https://docs.clarifeye.ai/backoffice/tag-extractors/delete-tag-extractor.md): Delete the `TagExtractor`. Related warehouse tables (`extracted_tags_table`, `alerts_tags_table`) are cleaned up on cascade.
- [Update tag extractor (auto-creates new version)](https://docs.clarifeye.ai/backoffice/tag-extractors/update-tag-extractor-auto-creates-new-version.md): Partial update. Version-bearing fields (changing any creates a new `TagExtractorVersion`): `tagging_tree`, `extraction_prompt`, `llm_model`, `enforce_single_tag`, `alerts_additional_instructions`.
- [Get a single chunk by id (version-agnostic)](https://docs.clarifeye.ai/backoffice/chunks/get-a-single-chunk-by-id-version-agnostic.md): Fetch one chunk row by its id, independent of which extractor version produced it. Chunk ids are random UUIDs (unique within the chunk table), so the lookup is unambiguous and does not require the extractor version.
- [List chunks extractors](https://docs.clarifeye.ai/backoffice/chunks-extractors/list-chunks-extractors.md)
- [Create chunks extractor](https://docs.clarifeye.ai/backoffice/chunks-extractors/create-chunks-extractor.md): Create a `ChunksExtractor`. A first `ChunksExtractorVersion` is created automatically and marked as default.
- [Retrieve chunks extractor](https://docs.clarifeye.ai/backoffice/chunks-extractors/retrieve-chunks-extractor.md)
- [Delete chunks extractor](https://docs.clarifeye.ai/backoffice/chunks-extractors/delete-chunks-extractor.md): Delete the `ChunksExtractor`. The related `extracted_chunks_table` is cleaned up on cascade.
- [Update chunks extractor (auto-creates new version)](https://docs.clarifeye.ai/backoffice/chunks-extractors/update-chunks-extractor-auto-creates-new-version.md): Partial update. Version-bearing fields: `maximum_chunk_size`, `minimum_chunk_size`, `page_as_separator`, `title_section_separator_mode`, `excluded_block_types`, `chunking_mode`.
- [List parsing extractors](https://docs.clarifeye.ai/backoffice/parsing-extractors/list-parsing-extractors.md)
- [Create parsing extractor](https://docs.clarifeye.ai/backoffice/parsing-extractors/create-parsing-extractor.md): Create a `ParsingExtractor`. A first version is created automatically and marked as default.
- [Retrieve parsing extractor](https://docs.clarifeye.ai/backoffice/parsing-extractors/retrieve-parsing-extractor.md)
- [Delete parsing extractor](https://docs.clarifeye.ai/backoffice/parsing-extractors/delete-parsing-extractor.md): Delete the `ParsingExtractor`. Related warehouse tables (`extracted_parsed_documents_table`, `extracted_blocks_table`) are cleaned up on cascade.
- [Update parsing extractor (auto-creates new version)](https://docs.clarifeye.ai/backoffice/parsing-extractors/update-parsing-extractor-auto-creates-new-version.md): Partial update. Version-bearing fields: `reducto_parsing_options`, `llm_model`, `use_fast_parsing_for_pdfs`.
- [List document filter extractors](https://docs.clarifeye.ai/backoffice/document-filter-extractors/list-document-filter-extractors.md)
- [Create document filter extractor](https://docs.clarifeye.ai/backoffice/document-filter-extractors/create-document-filter-extractor.md): Create a `DocumentFilterExtractor` — restricts a downstream pipeline branch to documents matching the configured filter.
- [Retrieve document filter extractor](https://docs.clarifeye.ai/backoffice/document-filter-extractors/retrieve-document-filter-extractor.md)
- [Delete document filter extractor](https://docs.clarifeye.ai/backoffice/document-filter-extractors/delete-document-filter-extractor.md)
- [Update document filter extractor (auto-creates new version)](https://docs.clarifeye.ai/backoffice/document-filter-extractors/update-document-filter-extractor-auto-creates-new-version.md): Partial update. Version-bearing field: `filter`.
- [List chunk tag filter extractors](https://docs.clarifeye.ai/backoffice/chunk-tag-filter-extractors/list-chunk-tag-filter-extractors.md)
- [Create chunk tag filter extractor](https://docs.clarifeye.ai/backoffice/chunk-tag-filter-extractors/create-chunk-tag-filter-extractor.md): Create a `ChunkTagFilterExtractor` — restricts a downstream pipeline branch to chunks carrying specific tags.
- [Retrieve chunk tag filter extractor](https://docs.clarifeye.ai/backoffice/chunk-tag-filter-extractors/retrieve-chunk-tag-filter-extractor.md)
- [Delete chunk tag filter extractor](https://docs.clarifeye.ai/backoffice/chunk-tag-filter-extractors/delete-chunk-tag-filter-extractor.md)
- [Update chunk tag filter extractor (auto-creates new version)](https://docs.clarifeye.ai/backoffice/chunk-tag-filter-extractors/update-chunk-tag-filter-extractor-auto-creates-new-version.md): Partial update. Version-bearing field: `filter`.
- [List document tag extractors](https://docs.clarifeye.ai/backoffice/document-tag-extractors/list-document-tag-extractors.md)
- [Create document tag extractor](https://docs.clarifeye.ai/backoffice/document-tag-extractors/create-document-tag-extractor.md): Create a `DocumentTagExtractor` — applies a flat set of metadata tags to each document.
- [Retrieve document tag extractor](https://docs.clarifeye.ai/backoffice/document-tag-extractors/retrieve-document-tag-extractor.md)
- [Delete document tag extractor](https://docs.clarifeye.ai/backoffice/document-tag-extractors/delete-document-tag-extractor.md): Delete the `DocumentTagExtractor`. The related `extracted_document_tags_table` is cleaned up on cascade.
- [Update document tag extractor (auto-creates new version)](https://docs.clarifeye.ai/backoffice/document-tag-extractors/update-document-tag-extractor-auto-creates-new-version.md): Partial update. Version-bearing fields: `tags`, `llm_model`.
- [List tag alerts extractors](https://docs.clarifeye.ai/backoffice/tag-alerts-extractors/list-tag-alerts-extractors.md)
- [Create tag alerts extractor](https://docs.clarifeye.ai/backoffice/tag-alerts-extractors/create-tag-alerts-extractor.md): Create a `TagAlertsExtractor` — runs LLM-based alerts over already-extracted tag rows.
- [Retrieve tag alerts extractor](https://docs.clarifeye.ai/backoffice/tag-alerts-extractors/retrieve-tag-alerts-extractor.md)
- [Delete tag alerts extractor](https://docs.clarifeye.ai/backoffice/tag-alerts-extractors/delete-tag-alerts-extractor.md): Delete the `TagAlertsExtractor`. The related `alerts_tags_table` is cleaned up on cascade.
- [Update tag alerts extractor (auto-creates new version)](https://docs.clarifeye.ai/backoffice/tag-alerts-extractors/update-tag-alerts-extractor-auto-creates-new-version.md): Partial update. Version-bearing fields: `instructions`, `llm_model`.
- [List object alerts extractors](https://docs.clarifeye.ai/backoffice/object-alerts-extractors/list-object-alerts-extractors.md)
- [Create object alerts extractor](https://docs.clarifeye.ai/backoffice/object-alerts-extractors/create-object-alerts-extractor.md): Create an `ObjectAlertsExtractor` — runs LLM-based alerts over already-extracted object rows.
- [Retrieve object alerts extractor](https://docs.clarifeye.ai/backoffice/object-alerts-extractors/retrieve-object-alerts-extractor.md)
- [Delete object alerts extractor](https://docs.clarifeye.ai/backoffice/object-alerts-extractors/delete-object-alerts-extractor.md): Delete the `ObjectAlertsExtractor`. The related `alerts_table` is cleaned up on cascade.
- [Update object alerts extractor (auto-creates new version)](https://docs.clarifeye.ai/backoffice/object-alerts-extractors/update-object-alerts-extractor-auto-creates-new-version.md): Partial update. Version-bearing fields: `instructions`, `llm_model`.
- [List imported object extractors](https://docs.clarifeye.ai/backoffice/imported-object-extractors/list-imported-object-extractors.md)
- [Create imported object extractor](https://docs.clarifeye.ai/backoffice/imported-object-extractors/create-imported-object-extractor.md): Create an `ImportedObjectExtractor` — holds objects imported from an external system (rather than extracted by an LLM).
- [Retrieve imported object extractor](https://docs.clarifeye.ai/backoffice/imported-object-extractors/retrieve-imported-object-extractor.md)
- [Delete imported object extractor](https://docs.clarifeye.ai/backoffice/imported-object-extractors/delete-imported-object-extractor.md): Delete the `ImportedObjectExtractor`. The related `imported_objects_table` is cleaned up on cascade.
- [Update imported object extractor (auto-creates new version)](https://docs.clarifeye.ai/backoffice/imported-object-extractors/update-imported-object-extractor-auto-creates-new-version.md): Partial update. Version-bearing field: `extractable_pydantic_class`.
- [List artifacts in the catalog](https://docs.clarifeye.ai/backoffice/artifacts/list-artifacts-in-the-catalog.md): List the project's artifact catalog (paginated). In-scope artifacts sort before out-of-scope ones, then by `display_order` and `slug`. Requires view permission.
- [Create a custom artifact](https://docs.clarifeye.ai/backoffice/artifacts/create-a-custom-artifact.md): Create a custom artifact (`semantic_type` is always `custom`; predefined artifacts are seeded by the platform). The slug must be unique within the project. An initial empty version is published automatically. Requires admin permission.
- [Read the cohesion guide](https://docs.clarifeye.ai/backoffice/artifacts/read-the-cohesion-guide.md): Read the default artifact snapshot's cross-artifact cohesion guide. `default_cohesion_guide` carries the platform default text so clients can preview what `mode=default` resolves to. Requires view permission.
- [Update the cohesion guide](https://docs.clarifeye.ai/backoffice/artifacts/update-the-cohesion-guide.md): Update the default snapshot's cohesion guide. When `cohesion_guide_mode` is `default`, `cohesion_guide_text` is cleared server-side. Requires admin permission.
- [Export the artifact catalog](https://docs.clarifeye.ai/backoffice/artifacts/export-the-artifact-catalog.md): Export the full artifact catalog — artifact metadata, complete version history (payloads included), and snapshot settings — for migration to another project. Requires view permission.
- [Import an artifact catalog](https://docs.clarifeye.ai/backoffice/artifacts/import-an-artifact-catalog.md): Import a full catalog (same shape as the export) into a project whose catalog is still empty — the import is rejected if the project already has catalog rows. Only `in_scope_latest` snapshots are supported. Requires admin permission.
- [Retrieve an artifact](https://docs.clarifeye.ai/backoffice/artifacts/retrieve-an-artifact.md): Retrieve one artifact with its definitions and the payload of the selected version (head by default; pass `version` to read an older one). Requires view permission.
- [Delete an artifact](https://docs.clarifeye.ai/backoffice/artifacts/delete-an-artifact.md): Delete an artifact and its versions. Rejected when the artifact's delete preconditions are not met (see `can_delete` on the summary). Requires admin permission.
- [Update a custom artifact](https://docs.clarifeye.ai/backoffice/artifacts/update-a-custom-artifact.md): Update a custom artifact's metadata (title, group, definitions). Only fields present in the request are touched. Predefined artifacts cannot be edited. Requires admin permission.
- [Remove an artifact from scope](https://docs.clarifeye.ai/backoffice/artifacts/remove-an-artifact-from-scope.md): Take the artifact out of the knowledge-store scope (it stays in the catalog and keeps its history). The brief artifact cannot be removed from scope. Requires admin permission.
- [Restore an artifact to scope](https://docs.clarifeye.ai/backoffice/artifacts/restore-an-artifact-to-scope.md): Put an out-of-scope artifact back in scope. Requires admin permission.
- [List artifact versions](https://docs.clarifeye.ai/backoffice/artifacts/list-artifact-versions.md): List all versions of an artifact, newest first, payloads included. Not paginated. Requires view permission.
- [Publish a new artifact version](https://docs.clarifeye.ai/backoffice/artifacts/publish-a-new-artifact-version.md): Publish a new head version with the given payload. The payload shape depends on the artifact's `technical_type` — string for `markdown` / `bpmn_xml`, object for `mental_map`, array for `playbook_list` / `design_template_list`. Requires admin permission.
- [Retrieve an artifact version](https://docs.clarifeye.ai/backoffice/artifacts/retrieve-an-artifact-version.md): Retrieve one version of an artifact by number. Requires view permission.
- [List design template files](https://docs.clarifeye.ai/backoffice/design-system-templates/list-design-template-files.md): List the project's design template reference files (paginated). Optionally filter to a single template via `template_id`. Requires project view permission.
- [Upload a design template file](https://docs.clarifeye.ai/backoffice/design-system-templates/upload-a-design-template-file.md): Upload a reference/example file and attach it to a design template. Requires project-admin permission.
- [Delete a design template file](https://docs.clarifeye.ai/backoffice/design-system-templates/delete-a-design-template-file.md): Delete a design template reference file from the project, removing it from storage. Requires project-admin permission.
- [Dry-run count of what an import would do](https://docs.clarifeye.ai/backoffice/connectors/dry-run-count-of-what-an-import-would-do.md): Enumerates provider metadata (no downloads) for the given folder/file selection and diffs it against already-imported documents. An empty selection falls back to the connection's stored selection. Enumeration is budgeted (item, request, and wall-clock caps): when `truncated` is true, `to_create`/`to…

## OpenAPI Specs

- [openapi-full](https://docs.clarifeye.ai/api-reference/openapi-full.yaml)
- [openapi-public](https://docs.clarifeye.ai/api-reference/openapi-public.yaml)

## Optional

- [Website](https://clarifeye.ai)