Skip to main content

Admin Panel

The Admin Panel is Talonic's platform administration surface, accessible from the user menu (Admin Dashboard) for Talonic platform administrators (superadmins). It is not the same as the workspace Admin role, which manages one workspace from Team Members and Workspace Settings. It provides organization management, user management, usage statistics, data clear and rebuild, and a cross-tenant master registry view.

The Admin Panel is the central hub for platform-wide operations. Organization management (the admin nav still labels organizations "Customers") lets you create, view, and delete organizations. User management provides a cross-tenant view of all platform users with the ability to remove accounts. The data clear & rebuild function wipes all data for a specific organization and reprocesses from scratch — useful during onboarding or after significant schema changes.

The Admin Panel operates across tenant boundaries, giving administrators visibility into all organizations on the platform. The usage statistics view aggregates cost and volume data across all organizations, making it straightforward to identify high-usage tenants, track platform growth, and forecast infrastructure needs. Usage data includes per-feature breakdowns (extraction, OCR, batch, matching) and daily cost trends across all tenants.

For best results, limit Admin Panel access to a small group of trusted platform operators. Use the master registry view to audit field definitions and schemas across tenants — this is particularly useful when standardizing extraction configurations or troubleshooting cross-tenant data quality issues.

The data clear and rebuild operation is designed for specific scenarios: initial onboarding when an organization uploads test documents that should not persist, significant schema changes that require reprocessing the entire corpus, or data quality issues where starting fresh produces better results than incremental fixes. Before executing a data clear, always confirm with the organization and verify that any approved data products have been exported to downstream systems, since the operation permanently removes all extraction history and job results.

  • Organization management — create, list, and delete organizations.
  • User management — view all users across tenants, remove accounts.
  • Usage statistics — platform-wide cost and usage aggregates.
  • Data clear & rebuild — wipe and reprocess all data for an organization.
  • Master registry — cross-tenant view of the Field Registry and schemas.
The data clear operation is irreversible. It deletes all documents, extractions, jobs, and results for the selected organization. Use with caution and only when a full reprocessing is genuinely needed.

Common Admin Workflows

The most common admin workflow is onboarding a new organization. Navigate to Organization management, create the organization, then share the workspace URL with the organization's team lead. As team members sign up with their company email domain, they appear on the Team page as pending members awaiting approval. The admin reviews and approves each member, assigning roles based on their responsibilities. Once the team is set up, the admin can create initial API keys and configure source connectors to get the organization started with document ingestion.

For troubleshooting, the master registry view is invaluable. It lets you inspect an organization's field registry, schemas, and extraction results from a single cross-tenant interface. If an organization reports low extraction quality, start by checking their field registry — a registry with mostly Candidate fields and low instruction coverage suggests the knowledge graph has not matured enough. Running a batch resolution followed by instruction synthesis often resolves the issue by promoting fields and generating master extraction instructions.

The Admin Panel also provides tools for platform capacity planning. By reviewing usage statistics across all organizations, administrators can identify growth trends, forecast compute and storage needs, and plan infrastructure scaling ahead of demand spikes. The per-organization breakdown reveals which organizations are the heaviest users and which features drive the most cost, helping prioritize optimization efforts where they have the greatest impact.

The Admin Panel is a UI surface at /admin, gated to Talonic platform administrators (superadmins). It is not exposed as a public /v1 API namespace: organization management, user management, usage statistics, data clear and rebuild, and the master registry are all driven from the admin-only screens rather than documented public endpoints. Tenant-scoped data remains accessible through the standard public API with an appropriately scoped key.

Frequently asked questions

What features does the Admin Panel provide?+
Organization management (create, list, delete organizations), user management (cross-tenant user view with account removal), usage statistics (platform-wide cost and volume aggregates), data clear and rebuild (wipe and reprocess all data for an organization), and cross-tenant master registry view (audit field definitions and schemas across tenants).
Who can access the Admin Panel?+
The Admin Panel is accessible only to Talonic platform administrators (superadmins), via the Admin Dashboard entry in the user menu. Workspace roles (Viewer, Member, Senior Member, and Admin) do not see it; a workspace Admin manages their own workspace from Team Members and Workspace Settings instead.
What does the data clear operation do?+
Data clear wipes all documents, extractions, jobs, results, and related data for a specific organization. It is irreversible and intended for full reprocessing scenarios during onboarding or after major schema changes. Always confirm with the organization before executing this operation.
Can I view usage across all organizations?+
Yes. The Admin Panel includes a master registry view that shows cross-tenant usage statistics, per-organization cost breakdowns, and platform-wide aggregates. This is useful for identifying high-usage tenants, tracking platform growth, and forecasting infrastructure needs.
How do I troubleshoot low extraction quality for an organization?+
Start by checking the organization's field registry via the master registry view. Look at the maturity distribution (Core, Proven, Candidate), instruction coverage, and unresolved occurrence count. A registry dominated by Candidate fields with low instruction coverage suggests the knowledge graph needs more data. Run batch resolution followed by instruction synthesis to promote fields and generate extraction directives. Then review the telemetry metrics — capture rate, resolve rate, and synthesize rate — to confirm improvement.

Related

Team Management
Usage