Core Concepts
How Vault, Legislate, Workbench, Workflows, integrations, and agents fit together.
TextMine is organized around connected work surfaces. Understanding the surface you are targeting makes API calls and agent plans much more reliable.
Product areas
| Area | Use it for |
|---|---|
| Vault | Store documents, classify document types, extract tags and metadata, ask questions, run reports, and trigger processing. |
| Legislate | Review the validated team-document archive after documents are published from Vault. |
| Workbench | Explore questions, upload or import files, orchestrate multi-step work, and work with user-enabled MCP providers inside the app. |
| Workflows | Automate repeatable work with triggers, ordered actions, optional conditions, and run history. |
| Playbooks | Apply reusable document review logic, negotiation guidance, policies, and checklists. |
| Records | Turn document evidence into structured business data, schemas, relationships, graphs, and review candidates. |
| Agents | Run configurable AI agents directly, from Workbench, or from Workflows. |
| Scribe | Generate documents and templates using fields and conditional logic. |
| Integrations | Import provider files, submit to external systems, call APIs or webhooks, and expose TextMine through MCP. |
Vault versus Legislate
Use Vault when the task starts with documents: upload, import, process, classify, extract, search, ask, report, tag, or reprocess.
Use Legislate when the task is about validated documents already published from Vault. Legislate is still a valid TextMine surface, but it is the archive of validated team documents rather than another name for Vault.
Documents
A document normally belongs to a Vault and can have:
- A document type.
- Extracted default fields.
- Custom metadata fields and tags.
- Processing state and evidence.
- Folder placement.
- Reports, workflow runs, playbook results, alerts, or exports connected to it.
Validated documents can later be published to Legislate, where they become part of the team-document archive.
Integrations and imports
TextMine supports both provider imports and TextMine-native uploads. Provider imports let connected systems such as Google Drive, SharePoint, and Notion supply files to Vault without manually downloading and re-uploading them. Native uploads are best when the caller already has the file bytes.
Workflows and agents
Workflows are for repeatable processes. Agents are for configurable AI work that can be run directly, from Workbench, or as part of a workflow. A good integration often combines both: use the API to ingest data, use an agent or playbook to analyze it, and use a workflow to make the process repeatable.