Skip to content
Changelog

Report a bug

Customgpt integration: operations for AI agents

Customgpt connects to Type.com as an integration. This page lists the 121 operations documented for Claude and Codex in Type.com: 57 read, 28 write, 36 destructive.

About Customgpt

CustomGPT.ai is a platform that enables users to create and integrate AI-powered chatbots tailored to their specific data and requirements.

Categories: Customer Support

How to connect Customgpt to Type.com

Access
Organization connection: one shared account for the workspace.

To add the connection, follow the steps in Space connections.

Documented operations

121 operations. Your connection's permissions determine which operations are available. API references describe the vendor surface; they do not expand your connection's credentials or access.

121 operations listed.

Agents

  • Read

    List all agents.

    Returns all agents in your account, sorted by creation date with the most recent first. Use this endpoint to get an overview of your agents or to retrieve agent IDs for other API calls. Results are paginated with a default page size of 10.

  • Read

    Get agent details.

    Returns the full configuration and current status for a specific agent. Use this to check processing status, view settings, or retrieve metadata about the agent.

  • Read

    Get agent statistics.

    Returns usage metrics and performance statistics for an agent, including total conversations, query counts, document statistics, and processing information. Use this for monitoring and reporting.

  • Write

    Create an agent.

    Creates a new agent by importing content from a sitemap URL or uploading a file. The imported content becomes the agent's knowledge base, which it uses to answer questions. The agent will begin processing the content immediately after creation.

  • Write

    Update an agent.

    Updates an existing agent's name or configuration settings. Use this to rename an agent or modify its basic properties without affecting its knowledge base.

  • Write

    Replicate an agent.

    Creates a complete copy of an existing agent, including its knowledge base, persona, and settings. Use this to create variations of an agent for testing, or to use an existing agent as a template for a new one.

  • Destructive

    Delete an agent.

    Permanently deletes an agent and all associated data, including its knowledge base, conversations, settings, and analytics. This action cannot be undone. Warning: This operation is irreversible. All conversations, sources, and settings will be permanently deleted.

Conversations

  • Read

    List conversations.

    Returns all conversations for an agent. Each conversation represents a chat session with a user and contains the full message history. Results are paginated and sorted by most recent activity.

  • Read

    Export conversation.

    Exports the complete conversation history (all prompts and agent responses) as a downloadable file. Use this to archive conversations, share transcripts, or analyze conversation content offline. The file format is selected by the format query parameter.

  • Read

    Get conversation messages.

    Returns all messages in a conversation, including user prompts, agent responses, timestamps, and citations. Use this to display conversation history or analyze past interactions.

  • Write

    Send message (OpenAI format).

    Sends a message using the OpenAI-compatible request and response format. Use this if you are migrating from OpenAI or want to use existing OpenAI client libraries. Supports streaming for real-time responses. Notes: This is a convenience endpoint for OpenAI compatibility.

  • Write

    Create a conversation.

    Creates a new conversation session for an agent. Returns a session ID that you'll use to send messages. You can optionally provide a name to help identify the conversation later. Notes: You can also create conversations implicitly by sending a message with a new session ID.

  • Write

    Send message.

    Sends a user message to an agent and returns the agent's response. Supports streaming for real-time display, file attachments for document analysis, and persona overrides for dynamic behavior. This is the primary endpoint for chat interactions.

  • Destructive

    Update conversation.

    Updates conversation metadata, such as the display name. Use this to rename conversations for easier organization and identification.

  • Destructive

    Delete conversation.

    Permanently deletes a conversation and all its messages. Use this to remove sensitive conversations or clean up test data. Warning: This action cannot be undone. All messages in the conversation will be permanently deleted.

Pages

  • Read

    List all documents.

    Returns all indexed documents in an agent's knowledge base. Each document represents a piece of content (webpage, PDF, uploaded file) that the agent can reference when answering questions. Results are paginated.

  • Read

    Get document labels.

    Returns all labels assigned to a document. Labels control which users can access answers derived from this document - users only see answers from documents matching their assigned labels. Notes: Requires Custom plan. Documents without labels are accessible to all users.

  • Read

    Get citation source preview.

    Returns a preview of the source document referenced by a citation. Use this to show users the original content that the agent used to generate a response.

  • Write

    Reindex a document.

    Re-crawls and re-indexes a document to update its content in the knowledge base. Use this when the source content has changed and you want the agent to use the updated version. Notes: Only works for URL-based documents. For uploaded files, delete and re-upload instead.

  • Destructive

    Delete a document.

    Permanently removes a document from an agent's knowledge base. The agent will no longer reference this content when answering questions. Use this to remove outdated or incorrect information. Warning: This action cannot be undone.

  • Destructive

    Replace document labels.

    Assigns labels to a document for access control. The provided label IDs replace any existing labels on the document. To remove all labels (making the document accessible to everyone), send an empty array. Notes: Maximum 50 labels per document.

Pages Metadata

  • Read

    Get document metadata.

    Returns metadata for a document, including its title, source URL, word count, and any custom metadata fields. Use this to display document information or manage your knowledge base.

  • Destructive

    Update document metadata.

    Updates custom metadata fields for a document. Use this to add tags, categories, or other organizational information that helps manage your knowledge base.

Agent Settings

  • Read

    Get agent settings.

    Returns the complete configuration for an agent, including persona instructions, response behavior, deployment options, and feature flags. Use this to review or back up an agent's configuration.

  • Read

    List persona versions.

    Returns the version history of an agent's persona. Every time the persona is updated, a snapshot is automatically saved, allowing you to view changes over time or restore a previous version. Results are paginated.

  • Read

    Get persona version.

    Returns the full text and metadata for a specific persona version. Use this to compare versions or review what instructions were active at a particular time.

  • Read

    List sub-personas.

    Returns generated sub-personas for one persona version and project-level overrides separately.

  • Read

    List skill versions.

    Returns the version history of one skill, newest first.

  • Read

    Get skill version.

    Returns the full text and metadata of one version of a skill.

  • Write

    Update agent settings.

    Updates an agent's configuration, including persona instructions, response format, citation style, and deployment settings. Notes: Only include the fields you want to change - omitted fields retain their current values.

  • Write

    Update sub-persona override.

    Creates or updates the project-level override for one sub-persona slug. Generated persona-version rows are not modified.

  • Destructive

    Delete sub-persona override.

    Deletes the project-level override for one sub-persona slug. Generated persona-version rows are not modified.

  • Destructive

    Activate a persona version.

    Activates a previous persona version, making it the current active persona. This creates a new version entry in the history (it doesn't overwrite), preserving the full audit trail. Use this to roll back to a known-good configuration.

  • Destructive

    Restore skill version.

    Makes one version of a skill the live skill body again.

Deployment Settings

  • Read

    Get deployment settings.

    Returns all deployment section configurations (embed, livechat, aiassistant, instantviewer, sge) for an agent. Missing settings are returned with their default values.

  • Write

    Update deployment settings.

    Updates a single deployment section for an agent. The section path parameter identifies which section to update (embed, livechat, aiassistant, instantviewer, or sge). Only include the fields you want to change — omitted fields retain their current values.

Agent Actions

  • Read

    List agent actions.

    GET /api/v1/projects/{projectId}/actions

  • Read

    List the agent's custom External APIs.

    GET /api/v1/projects/{projectId}/actions/external-apis

  • Read

    Get a custom External API.

    GET /api/v1/projects/{projectId}/actions/external-apis/{integrationId}

  • Write

    Create a custom action (MCP).

    POST /api/v1/projects/{projectId}/actions/custom

  • Write

    Add a custom External API.

    Creates the connection from an OpenAPI schema, given as an uploaded file or an HTTPS URL. The agent calls it only while Plan & Act and Smart Tasks are enabled with external connections allowed (see available in the list response).

  • Write

    Replace a custom External API's OpenAPI schema.

    Takes the same openapiurl (JSON) or openapifile (multipart/form-data) field as create; exactly one of them is required.

  • Destructive

    Update a custom action configuration.

    PUT /api/v1/projects/{projectId}/actions/custom/{actionKey}

  • Destructive

    Delete a custom action.

    DELETE /api/v1/projects/{projectId}/actions/custom/{actionKey}

  • Destructive

    Update built-in action settings.

    PUT /api/v1/projects/{projectId}/actions/builtin/{actionKey}/settings

  • Destructive

    Update a custom External API.

    Renames it, replaces its API key, or enables/disables it. At most 5 External APIs can be active at once.

  • Destructive

    Delete a custom External API.

    DELETE /api/v1/projects/{projectId}/actions/external-apis/{integrationId}

Multi Agent

  • Read

    List child agents.

    Returns all agents currently assigned to this Multi-Agent, including their name and generation flag.

  • Write

    Assign child agents.

    Assigns one or more agents as children of this Multi-Agent. Enforces plan limits, team ownership, and prevents assigning Multi-Agent projects as children.

  • Destructive

    Bulk unassign child agents.

    Removes multiple child agents from this Multi-Agent in a single request. Returns 422 if the operation would leave no children, or if any specified agent is not currently assigned.

  • Destructive

    Unassign a child agent.

    Removes a single child agent from this Multi-Agent. Returns 422 if this is the last remaining child, or 404 if the agent is not currently assigned.

Tags

  • Read

    List all tags.

    Returns all tags configured for an agent, along with the users assigned to each tag. Use this to review your access control configuration or build a tag management interface. Tags are called labels in the API, so paths and fields use label (for example labelId and labels).

  • Read

    Get tag details.

    Retrieves a specific tag, including its name and the list of users assigned to it. Tags are called labels in the API, so paths and fields use label (for example labelId and labels).

  • Write

    Create tags.

    Creates one or more new tags for document access control. Accepts an array of tag names, allowing bulk creation. After creating tags, assign them to documents and users to control access.

  • Destructive

    Assign users to a tag.

    Sets which users are assigned to each tag. The provided user list becomes the source of truth - users not included in the list are removed from that tag, and new users are added. Tags are called labels in the API, so paths and fields use label (for example labelId and labels).

  • Destructive

    Update a tag name.

    Updates the name of an existing tag. User and document assignments are preserved. Tags are called labels in the API, so paths and fields use label (for example labelId and labels).

  • Destructive

    Delete a tag.

    Permanently deletes a tag and removes all associated assignments (both user-to-tag and document-to-tag mappings). Documents that lose their only tag will become accessible to everyone.

  • Destructive

    Remove users from tags.

    Removes specific users from one or more tags without affecting other users' assignments. Use this when offboarding users or revoking access to specific content. Tags are called labels in the API, so paths and fields use label (for example labelId and labels).

Webpage Awareness

  • Read

    List webpage context pages.

    Returns all webpage context entries for an agent, with optional URL filtering and pagination. Requires the Webpage Awareness tool to be enabled on the agent.

  • Write

    Bulk update page messages.

    Updates automessage and/or displaymessage for one or more webpage context entries. Requires the Webpage Awareness tool to be enabled on the agent.

  • Destructive

    Delete webpage context pages.

    Deletes webpage context entries for an agent. Pass pageids to delete specific pages, or omit the body to delete all pages for the agent. Requires the Webpage Awareness tool to be enabled on the agent.

Message

  • Read

    Get message details.

    Returns the complete details for a single message, including the user's prompt, the agent's response, timestamps, citations, and any attached metadata. Use this to retrieve specific messages for display or analysis.

  • Read

    Get message claims.

    Returns the factual claims extracted from an agent's response. Each claim is a discrete statement that can be independently verified against the source documents. Use this for fact-checking or building trust indicators.

  • Read

    Get message trust score.

    Returns a verification trust score for a message, calculated by checking how well the agent's claims are supported by the source documents. Higher scores indicate better-grounded responses.

  • Write

    Verify message accuracy.

    Triggers a fact-checking verification process for a message's claims. The system compares each claim against the source documents and reports which claims are supported, partially supported, or unsupported.

  • Destructive

    Update message feedback.

    Records user feedback (thumbs up/down) for a message. Use this to collect quality signals that help identify which responses are helpful and which need improvement.

Tasks

  • Read

    List tasks.

    Returns all Plan & Act mode tasks for an agent, paginated. Tasks are ordered by most recent activity.

  • Read

    Poll task.

    Returns the current processing state of a task. While the task is running, returns status: processing with any stream events flushed since the last poll.

  • Read

    Export task.

    Exports the full task conversation history (all prompts and agent responses) as a downloadable file. The file format is selected by the format query parameter.

  • Write

    Create task.

    Creates a Plan & Act task and submits its first prompt in one call. Returns 202 Accepted. Sessions can run for minutes or longer, so callers must poll GET /projects/{projectId}/tasks/{taskId} for progress events rather than holding a connection open.

  • Destructive

    Update task.

    Updates task metadata, such as the display name. Use this to rename tasks for easier organization and identification. The display name is the only mutable field exposed via the API.

  • Destructive

    Delete task.

    Permanently deletes a task and all its messages. Use this to remove sensitive tasks or clean up test data. Warning: This action cannot be undone. All messages in the task will be permanently deleted from the user-facing API.

Task Messages

  • Read

    List task messages.

    Returns all messages in a task, including user prompts, agent responses, timestamps, and citations. Use this to display task history or analyze past interactions. Results are paginated and ordered by most recent first.

  • Read

    Get task message.

    Returns the complete details for a single message, including the user's prompt, the agent's response, timestamps, citations, and any attached metadata. Use this to retrieve specific messages for display or analysis.

  • Write

    Submit tool outputs.

    Resumes a task paused on awaitingtoolresults by submitting the results of the function calls requested by the agent. All pending toolcallids must be answered in one request.

  • Write

    Stop response.

    Stops the response a task is currently generating. Whatever already ran is still saved and billed, and the plan is parked so the next message can pick it up. Returns 204 No Content; poll the task for the settled result.

  • Write

    Send follow-up message.

    Submits a follow-up prompt to an existing task. The task must not currently be processing a previous message. Returns 202 Accepted; poll the task for progress. Returns 409 if the task is locked by an active session.

Task Files

  • Read

    List message files.

    Returns all files associated with a specific task message - both user-uploaded sources and AI-generated artifacts. Use the type field to distinguish between upload and artifact. Generated artifacts expire after a configurable TTL (default 24 h).

  • Read

    Download message file.

    Generates a pre-signed URL for an agent-generated artifact and redirects to it. The redirect target is valid for 1 hour.

  • Destructive

    Delete message file.

    Deletes an agent-generated artifact from a task message.

Citations

  • Read

    Get citation metadata.

    Returns metadata for a specific citation, including the source document's title, description, URL, and preview information. Use this to display source attribution or allow users to verify the agent's sources.

Sources

  • Read

    List sources.

    Returns all data sources connected to an agent. Each source represents an origin for documents - such as a sitemap, Google Drive folder, SharePoint site, or uploaded files. Use this to manage what content feeds into an agent's knowledge base.

  • Write

    Add a source.

    Connects a new data source to an agent's knowledge base. You can add content via sitemap URL, file upload, or integration connection (Google Drive, SharePoint, etc.). The system will begin indexing the content immediately.

  • Destructive

    Update source settings.

    Updates configuration for a data source, such as auto-sync frequency, crawl depth, or file filters. Use this to fine-tune how the source is indexed and kept up to date.

  • Destructive

    Delete a source.

    Removes a data source and all its documents from an agent's knowledge base. Use this to disconnect content that's no longer relevant or to clean up after testing. Notes: To delete individual documents without removing the entire source, use the Delete Document endpoint instead.

  • Destructive

    Trigger instant source sync.

    Triggers an immediate re-sync of a data source, refreshing all its documents with the latest content. Use this when you know the source has been updated and don't want to wait for the scheduled sync. Notes: Only available for sources that support syncing (sitemaps, integrations).

Reports & Analytics

  • Read

    Get customer intelligence.

    Returns AI-analyzed insights about your users, including common intents, emotional sentiment, frequently discussed topics, and emerging trends. Use this to understand what users are asking about and how they're feeling.

  • Read

    Get traffic analytics.

    Returns a breakdown of conversation volume by deployment channel (e.g. web widget, API, Slack, WhatsApp) over the requested time window. Use the filters query parameter to scope the report.

  • Read

    Get query analytics.

    Returns aggregate query metrics, including total query volume, success rates, average response times, and failure reasons. Use this to monitor agent performance and identify issues.

  • Read

    Get conversation analytics.

    Returns conversation metrics, including total conversations, average duration, messages per conversation, and completion rates. Use this to understand how users engage with your agent.

  • Read

    Get analytics chart data.

    Returns time-series data formatted for charts, with daily, weekly, or monthly breakdowns of key metrics.

  • Read

    Export leads.

    Exports lead information captured from conversations, including email addresses, names, and any custom fields collected. Use this to sync leads with your CRM or marketing tools.

  • Read

    Export leads for a conversation.

    Exports every lead captured in a conversation as a downloadable file in the requested format.

  • Read

    Export a single collated lead for a conversation.

    Returns one merged lead built from all lead rows in the conversation.

Agent Licenses

  • Read

    List licenses.

    Returns all access licenses configured for an agent. Licenses control who can interact with the agent and what permissions they have. Use this to manage access distribution.

  • Read

    Get license details.

    Returns the full details for a specific license, including permissions, usage statistics, status, and expiration date. Use this to audit or troubleshoot access issues.

  • Write

    Create a license.

    Creates a new access license for an agent with specified permissions and optional expiration. Use this to grant controlled access to external users or systems.

  • Destructive

    Update a license.

    Updates a license's settings, such as permissions, expiration date, or active status. Use this to modify access without creating a new license.

  • Destructive

    Delete a license.

    Revokes and permanently removes an access license. Any users or systems using this license will immediately lose access to the agent. Warning: This immediately revokes access for anyone using this license.

Users

  • Read

    Get current user profile.

    Returns profile information for the currently authenticated user, including account details and settings.

  • Read

    Search team members.

    Searches for team members by email address or user ID. Use this to find users when assigning permissions or managing team access. Notes: Requires Owner or Admin role.

  • Write

    Update user profile.

    Updates profile settings for the currently authenticated user. Use this to modify account preferences or personal information.

Limits

  • Read

    Get account limits.

    Returns your current usage and plan limits for agents, storage (words), and monthly queries. Use this to monitor consumption, plan for scaling, or display usage dashboards to your users.

Billing

  • Read

    Get current plan details.

    Returns the active subscription plan for your account, including billing cycle dates, trial status, plan options, and active addons. Returns null data when no active subscription exists.

  • Read

    List payment methods.

    Returns all payment methods attached to your account, including type, display name, card details, and which is the default.

  • Read

    List invoices.

    Returns paginated invoices for your account. Invoice records are stored locally and do not require a Stripe API call. Use the page and limit query parameters to paginate.

  • Read

    Download an invoice.

    Returns the Stripe-hosted PDF for the specified invoice. The invoice ID must belong to your account.

Teams

  • Read

    List all teams the authenticated user belongs to.

    Returns a paginated list of all teams the authenticated user is a member of.

  • Write

    Switch active team.

    Switches the authenticated user's active team context. Subsequent requests will operate in the context of the new team.

  • Destructive

    Update a team name.

    Updates the name of a team. Only the team owner or a member with the update permission can perform this action.

Team Members

  • Read

    List team members.

    Returns a paginated list of all members belonging to the specified team, including their assigned roles.

  • Destructive

    Update a team member's role.

    Changes the role assigned to a team member. Only the team owner or a member with the appropriate permission can perform this action.

  • Destructive

    Remove a team member.

    Removes a member from the team. Only the team owner or a member with the appropriate permission can perform this action.

Team Invitations

  • Read

    List pending invitations.

    Returns a paginated list of all pending invitations for the specified team.

  • Write

    Invite a new member.

    Sends an invitation email to the specified address. The recipient must accept the invitation before they become a team member.

  • Write

    Resend an invitation.

    Cancels the existing invitation and sends a new one to the same email address with the same role.

  • Destructive

    Cancel an invitation.

    Cancels a pending team invitation. The invited person will no longer be able to join via this invitation link.

Team Roles

  • Read

    List roles.

    Returns all roles that can be assigned to members within this team. Includes both global assignable system roles (Administrator, Member, Chat-only) and the team's own custom roles. Super Admin and Owner are excluded as they are not assignable.

  • Write

    Create a custom role.

    Creates a new custom role for the team with the specified permissions. Role names cannot match reserved role names (Owner, Administrator, Member).

  • Destructive

    Update a custom role.

    Updates an existing custom role's name, description, and permissions. Only roles belonging to this team can be updated.

  • Destructive

    Delete a custom role.

    Deletes a custom role belonging to this team. Reserved system roles cannot be deleted, and a role cannot be deleted while it still has members assigned, has pending invitations, or is set as an organization's default SSO role.

See How connections work for access and permissions, or browse all integrations.