Skip to main content
Workbench is an in-app AI workspace with a backend capability registry. Each capability has a purpose, expected inputs, outputs, approval rules, and sometimes an asynchronous wait step. Use this page to understand what Workbench can do. External agents should use TextMine MCP server or API and developer docs when they need direct API or MCP tool access.

Capability rules

  • Read capabilities can usually run without approval.
  • Mutating configuration or durable data requires approval.
  • Long-running actions have matching wait capabilities.
  • Workbench should inspect or search documents before acting on a vague source scope.
  • Saving files into Vault is different from using files as temporary Workbench context.

Document and Vault capabilities

CapabilityWhat it doesNotes
inspect_vault_documentsReads document metadata, IDs, Vault scope, and processing state.Use early when a task depends on Vault documents.
search_accessible_vault_documentsSearches documents and extracted tags across accessible Vaults.Resolves source scopes before asking Vault, creating reports, or running workflow-backed actions.
ask_vaultAnswers using Vault documents, extracted tags, and optional uploaded reference text.Read-only analysis, comparison, summarization, and evidence-backed answers.
answer_reference_documentAnswers directly from uploaded reference text without requiring Vault processing.Good for quick uploaded-file analysis.
import_uploaded_documentsImports Workbench-uploaded files into a selected Vault.Requires approval and uses the durable Vault document pipeline.
reprocess_documentsQueues selected Vault documents for reprocessing.Requires approval; use after configuration or extraction changes.
wait_for_document_processingWaits for document or tag processing to finish.Used after custom tag runs, imports, or reprocessing.

Legislate and comparison capabilities

CapabilityWhat it doesNotes
read_legislate_documentsReads active Legislate/team documents.Legislate is the validated team-document archive, not a Vault.
compare_legislate_vault_documentsCompares Legislate documents with Vault documents.Use when the user asks about published documents versus Vault source documents.

MCP provider capabilities

CapabilityWhat it doesNotes
list_mcp_providersLists enabled MCP providers for the Workbench session.Shows connection status, Workbench enablement, and capabilities.
list_mcp_foldersLists folders from a connected file-storage provider.Requires a provider with folder listing capability.
list_mcp_filesLists or searches files in a provider folder.Use before selecting files for import.
import_mcp_documentsImports selected provider files into the current Workbench chat.Imports temporary Workbench context; saving to Vault is a separate approved step.
The provider import path is intentionally bounded: Workbench imports selected files, not entire provider repositories. The backend limits a single import batch to selected files and a total size cap.

Playbooks

CapabilityWhat it doesNotes
read_playbooksLists or searches available playbooks.Read-only inventory.
create_playbookCreates a reusable playbook from source text or rules.Requires approval.
run_playbookRuns an existing playbook against selected Vault documents.Asynchronous; use for reusable review logic.

Document types, tags, and extraction setup

CapabilityWhat it doesNotes
read_document_typesLists document types for a Vault or workspace.Read-only inventory.
create_document_typeCreates a document type or adds default tag definitions.Requires approval.
delete_document_typeDeletes a custom document type.Requires approval.
setup_image_transcriptionCreates or reuses an image type and default image tags.Requires approval; used for embedded image transcription/classification.
create_custom_tagsCreates or reuses custom tags/questions.Requires approval because it changes reusable extraction configuration. See Tags and extraction.
run_custom_tagsRuns tags/questions against selected documents or a Vault.Requires approval; often followed by wait_for_document_processing.
run_table_extractionQueues table or line-item extraction.Asynchronous; followed by wait_for_table_extraction.
run_entity_extractionQueues entity extraction/resolution.Asynchronous; followed by wait_for_entity_extraction.
read_vault_entity_graphReads entities and relations from a Vault.Read-only graph data.

Reports and templates

CapabilityWhat it doesNotes
create_reportCreates a report, table, comparison, summary, or analysis over selected documents.Asynchronous; should honor resolved source scope and carry document context into the report.
wait_for_report_completionWaits for a report job to complete.Reads status and result.
fill_templateFills an uploaded Word, Excel, CSV, text, form, or spreadsheet template.Uses uploaded template files and conversation context.
synthesize_workbench_resultProduces a partial answer from successful prior steps if a dependent analyzer failed.Fallback for resilient task completion.

Workflows and agents

CapabilityWhat it doesNotes
read_workflowsLists available workflows.Read-only inventory.
create_workflowCreates a reusable workflow using the workflow block catalog.Requires approval; should preserve the selected Vault or document scope and surface warnings before creation. See Workflow blocks.
run_workflowRuns an existing workflow or one-off workflow-backed action.Asynchronous; followed by wait_for_workflow_completion; should confirm scope before side-effecting runs.
cleanup_one_off_workflowSoft-deletes a temporary one-off workflow after completion.Host-inserted cleanup.
read_agentsLists on-demand agents.Read-only inventory.
create_agentCreates an on-demand agent.Requires approval.
run_agentRuns an existing on-demand agent against selected documents.Requires approval; followed by wait_for_agent_completion.

Records and schemas

CapabilityWhat it doesNotes
inspect_record_schemasReads accessible record schemas.Use before record mutation.
lookup_recordsReads or searches business records.Read-only.
upsert_recordCreates or updates business records.Requires approval.
update_record_schemaCreates or replaces record schemas.Requires approval.

Workbench skills and task lifecycle

CapabilityWhat it doesNotes
read_workbench_skillsReads saved Workbench skills from task context.Use when the user references recurring instructions or review style.
apply_workbench_skillApplies saved skill guidance to planning and execution.Guidance-only capability.
verify_goal_completionVerifies that completed task steps satisfy the original goal.Used near the end of a plan.
save_workbench_artifactSaves a result, report, table, or structured output back to the session.Final persistence step.
ask_for_approvalPauses for user approval before a proposed action.Reserved for host-created approval steps.

Safe-use guidance for agents

Agents should return the capability names they used, the IDs they touched, and any approvals they requested. For durable mutations, include enough context for audit: Vault IDs, document IDs, workflow IDs, run IDs, record IDs, report IDs, provider IDs, and imported file names.