CustomGPT.ai is a platform that enables users to create and integrate AI-powered chatbots tailored to their specific data and requirements.
CustomGPT.ai is a platform that enables users to create and integrate AI-powered chatbots tailored to their specific data and requirements. On Nagent, Customgpt is exposed as a fully-configurable ai chatbots integration that any agent can call — 40 actions, and API key authentication. No code is required to wire Customgpt into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use Customgpt to automate the kinds of tasks ai chatbots teams previously handled manually. Concrete examples — each one is a single agent step in Nagent — include:
Every action and trigger is paired with a structured input/output schema (visible in the sections below), so when you wire Customgpt into Helix — our agentic agent builder — the editor knows exactly what each step expects and produces. Configure once, deploy anywhere across your Nagent agents.
Every operation an agent can call against Customgpt, with input parameters and output schema. Drop these into any step of an agent built in Helix.
CUSTOMGPT_ACTIVATE_PERSONA_VERSIONRestore a previous persona version for a CustomGPT agent. 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. Requires Custom plan.
Input parameters
The version number of the persona to activate. This must be a valid version from the persona history.
The unique identifier of the agent (formerly known as project). Obtain this from the List Projects action.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_ADD_SOURCEAdd a data source to a CustomGPT agent's knowledge base. Connects content via sitemap URL, file upload, or integration. The system begins indexing immediately after creation. Use when adding documentation, FAQs, or knowledge content to an agent.
Input parameters
File to upload as a source (PDF, DOC, TXT, etc.). Required if sitemap_path is not provided.
The unique identifier of the agent (formerly known as project) to add the source to.
URL of the sitemap to use as a source (e.g., 'https://docs.example.com/sitemap.xml'). Required if file is not provided.
Whether to anonymize the data in the source.
Whether to enable OCR (Optical Character Recognition) for extracting text from images in the file.
Whether to enable vision processing for images in the file source. Allows the agent to analyze and understand image content.
Whether to retain file data after processing.
Type of image extraction from website.
Whether to compress images for vision processing. Reduces storage and improves performance.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_CLONE_PROJECTTool to clone a CustomGPT agent (project). 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.
Input parameters
The unique agent identifier of the project to clone
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_CREATE_CONVERSATIONTool to create a new conversation session for a CustomGPT agent. Use this when starting a new chat interaction - it returns a session ID that you'll use to send messages. Optionally provide a name to help identify the conversation later.
Input parameters
Optional name to identify the conversation. Helps organize and reference conversations later. If not provided, a default name will be assigned.
The unique identifier of the agent (formerly known as project). Obtain this from the List Projects action.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_CREATE_PROJECTTool to create a new CustomGPT agent from a sitemap URL or file upload. The agent immediately begins processing the content to build its knowledge base. Use when you need to create a new AI agent with custom knowledge from web content or documents. Either sitemap_path or file must be provided.
Input parameters
File to upload for the agent's knowledge base. Either file or sitemap_path must be provided, not both.
Name for the new agent. This will be the display name of the agent.
URL of sitemap to import content from. The agent will crawl and index content from this sitemap. Either sitemap_path or file must be provided, not both.
Whether to anonymize data in the agent's knowledge base. Use this to protect sensitive information.
Whether to enable OCR (Optical Character Recognition) for extracting text from images and scanned documents.
Whether to enable vision processing for images in the file source. Allows the agent to process and understand images.
Whether to retain file data after processing. If false, only extracted text is kept.
Whether to compress images for vision processing. Reduces storage and processing costs for image-heavy content.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_DELETE_PAGETool to delete a document from a CustomGPT agent's knowledge base. Permanently removes a document and 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.
Input parameters
The page id
The unique identifier of the agent (formerly known as project).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_DELETE_PROJECTTool to delete a CustomGPT project by ID. Use when you need to permanently remove an existing agent after confirming the ID.
Input parameters
Unique ID of the agent (project) to delete
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_DELETE_PROJECT_LICENSEDeletes a license from a CustomGPT project/agent. Requires numeric project ID and license ID. This action is idempotent - it succeeds even if the license doesn't exist (404). The project must have licenses enabled in its plan for this endpoint to work properly.
Input parameters
Unique identifier of the license to delete from the project
Numeric ID of the CustomGPT agent/project (as string, e.g., '90631'). The API requires integer-formatted project IDs.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_DELETE_SOURCETool to delete a data source from a CustomGPT agent. Removes the source and all its documents from the agent's knowledge base. Use this to disconnect content that's no longer relevant or to clean up after testing.
Input parameters
The unique identifier of a source to delete.
The unique identifier of the agent (formerly known as project).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_EXPORT_LEADSExport leads from a CustomGPT project. Returns lead information captured from conversations including email addresses, names, phone numbers, and custom fields. Supports pagination and date range filtering. Use this to sync leads with CRM or marketing tools.
Input parameters
Page number for pagination (≥1). If not specified, returns the first page.
Number of items per page (1-500). Defaults to 100 if not specified.
End date for filtering leads (ISO 8601 format, e.g., '2024-12-31T23:59:59Z'). Only leads up to this date will be included.
The unique ID of the project to export leads from.
Start date for filtering leads (ISO 8601 format, e.g., '2024-01-01T00:00:00Z'). Only leads from this date onwards will be included.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_GET_MESSAGETool to get message details from a CustomGPT conversation. Returns the complete details for a single message, including the user's prompt, the agent's response, timestamps, citations, and any attached metadata.
Input parameters
The message id of the message
The ID of the agent to get the message for
The session ID of the conversation to get the message from
Fields to expand in the response.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_GET_MESSAGE_TRUST_SCORETool to retrieve verification trust score for a message in a CustomGPT conversation. Returns a score calculated by checking how well the agent's claims are supported by source documents. Higher scores indicate better-grounded responses with stronger evidence.
Input parameters
The message ID of the message to get the trust score for.
The ID of the agent to get the message trust score for.
The session ID of the conversation containing the message.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_GET_PAGE_METADATATool to get document metadata including title, source URL, word count, and custom metadata fields. Use this to display document information or manage your knowledge base.
Input parameters
The unique identifier of the page.
The unique identifier of the agent (formerly known as project).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_GET_PLUGINSTool to retrieve plugin details for a specific CustomGPT agent (project). Use when you need to inspect plugin configuration, status, and metadata for an agent.
Input parameters
The unique agent id to retrieve plugin details for.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_GET_PROJECTTool to 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.
Input parameters
The width of the embed code. Defaults to 100%.
The height of the embed code. Defaults to auto.
The unique agent identifier.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_GET_PROJECT_LICENSETool to retrieve a license for a specific project. Use when you need to fetch license details by license ID.
Input parameters
Unique identifier of the license to retrieve.
Unique identifier of the project to which the license belongs.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_GET_PROJECT_SETTINGSRetrieve configuration settings for a specific CustomGPT agent/project. Returns settings including: chatbot avatar, background, default prompt, example questions, response source, language, and branding preferences. Use this to inspect agent configuration, audit settings, or retrieve values before making updates. Note: Some newly created projects may not have settings initialized yet and will return a 404.
Input parameters
The unique ID of the agent/project whose settings to retrieve
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_GET_REPORT_ANALYSISTool to retrieve analytics chart data for a CustomGPT project. Returns time-series data formatted for charts, with daily or weekly breakdowns of key metrics including conversation counts, query counts, and queries-per-conversation ratios. Use this to generate usage reports, track project engagement over time, or visualize chatbot performance trends.
Input parameters
List of metrics to include in the response. Choose from: conversations (total conversation count), queries (total query count), or queries_per_conversation (average queries per conversation). You can request one or multiple metrics.
Interval for aggregating analytics data.
The ID of the agent/project to get analytics for
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_GET_REPORT_CONVERSATIONSTool to get conversation analytics for a CustomGPT project. Returns conversation metrics including total conversations, average queries per conversation, and other engagement statistics. Use this to understand how users engage with your agent and analyze conversation patterns over time.
Input parameters
Filters to return conversation metrics for. Accepts a JSON array format (as a string). An empty array '\[\]' is valid and returns all conversation metrics.
The ID of the agent to get conversations analytics for. Obtain this from the List Projects action.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_GET_REPORT_INTELLIGENCETool to get customer intelligence for a CustomGPT project. Returns AI-analyzed insights about users including common intents, emotional sentiment, frequently discussed topics, and emerging trends. Use this to understand what users are asking about and identify patterns in user behavior.
Input parameters
Page number for pagination (≥1). Defaults to 1 if not specified.
Filter results by Lead Captured status (1 for captured, 0 for not captured). Multiple values allowed.
Number of items per page (1-1000). Defaults to 100 if not specified.
Filter results by User Location (country codes or names). Multiple values allowed.
Filter results by Query Sent By (user IDs). Multiple values allowed.
Filter results by Verified Claims Score as range (format: min-max, e.g., '0-100').
End date for filtering data (ISO 8601 format recommended).
Filter results by Query Language. Multiple values allowed.
The ID of the project to get customer intelligence for.
Start date for filtering data (ISO 8601 format recommended).
Filter results by CRM ID. Multiple values allowed.
Filter results by User Intent (e.g., 'informational', 'transactional'). Multiple values allowed.
Filter results by User Emotion (e.g., 'positive', 'negative', 'neutral'). Multiple values allowed.
Filter results by Risk: Fidelity (e.g., 'unavailable', 'low', 'high'). Multiple values allowed.
Filter results by Content Source (e.g., 'in-context'). Multiple values allowed.
Filter results by Deployment source. Multiple values allowed.
Filter results by Risk: Jailbreak (e.g., 'unavailable', 'low', 'high'). Multiple values allowed.
Filter results by Risk: Profanity (e.g., 'unavailable', 'low', 'high'). Multiple values allowed.
Filter results by Stakeholder Status (e.g., 'APPROVED'). Multiple values allowed.
Filter results by Risk: Prompt Leakage (e.g., 'unavailable', 'low', 'high'). Multiple values allowed.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_GET_REPORT_TRAFFICTool to retrieve traffic analytics for a CustomGPT agent/project. Returns user traffic metrics including unique visitors, session counts, geographic distribution, and device types. Use this to understand who's using your agent and how they're accessing it.
Input parameters
Filters to apply when retrieving traffic metrics. Pass an empty array to get all traffic data without filters.
The ID of the agent/project to get traffic analytics for.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_GET_STATSTool to get agent statistics. Returns usage metrics and performance statistics for an agent, including total conversations, query counts, document statistics, and processing information. Use when you need to monitor agent performance or generate usage reports.
Input parameters
The unique identifier of the agent (formerly known as project).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_GET_USAGE_LIMITSGet account usage limits showing current usage vs. maximum allowed for projects, storage credits, and API queries. This returns how many projects, storage credits (characters indexed), and queries you've used compared to your account's maximum limits. Use this to monitor quota consumption.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_GET_USER_PROFILETool to retrieve the current user's profile information. Use when you need to display or verify authenticated user details after login.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_LIST_CONVERSATION_MESSAGESRetrieves all messages from a CustomGPT conversation, including both user queries and AI responses. Use this to view the complete chat history for a specific conversation session. Returns an empty list if the conversation doesn't exist or has no messages.
Input parameters
The unique numeric identifier of the CustomGPT project (agent). Obtain this from the List Projects action.
The unique session identifier (UUID format) of the conversation. Obtained when creating a new conversation or listing conversations.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_LIST_PAGESLists all documents in a CustomGPT agent's knowledge base. Returns indexed content including webpages, PDFs, and uploaded files that the agent can reference. Supports filtering by crawl/index status and pagination. Use this to audit knowledge sources or verify successful document ingestion.
Input parameters
Page number to return. Defaults to 1 if not specified.
Number of documents to return per page. Defaults to 20 if not specified.
Order direction for sorting pages by ID.
The unique agent identifier. Obtain this from the List Projects action.
Status values for crawl and index operations.
Status values for crawl and index operations.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_LIST_PERSONASTool to list persona versions for a CustomGPT agent. Use when you need to view 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. Requires Custom plan.
Input parameters
Page number to return (≥1). If not specified, returns the first page.
Limit the number of persona versions to return per page. Defaults to 20.
The unique agent identifier. Obtain this from the List Projects action.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_LIST_PROJECT_LICENSESList all licenses for a CustomGPT project/agent. Returns an array of license objects with details like ID, type, status, and timestamps. Returns an empty array if the project has no licenses or if licenses are not enabled for the project. Use this when you need to check what licenses exist for a specific project/agent.
Input parameters
The unique identifier of the CustomGPT project (agent). Must be a numeric ID (e.g., '90631').
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_LIST_PROJECTSLists all CustomGPT projects (agents) for the authenticated user. Returns projects with full details including ID, name, type, chat status, and timestamps. Supports pagination via the 'page' parameter. Use this to discover available projects or iterate through all projects.
Input parameters
Page number for pagination (≥1). If not specified, returns the first page. Results are sorted by creation date (newest first).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_LIST_SOURCESTool to list all data sources connected to an agent. Returns sources from various origins like sitemaps, Google Drive folders, SharePoint sites, or uploaded files. Use this to manage what content feeds into an agent's knowledge base.
Input parameters
The unique identifier of the agent (formerly known as project).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_REINDEX_PAGETool to reindex a document in CustomGPT knowledge base. Re-crawls and re-indexes a URL-based document to update its content. Use this when the source content has changed and you want the agent to use the updated version. Only works for URL-based documents.
Input parameters
The page id of the document to reindex.
The unique identifier of the agent (formerly known as project).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_SEARCH_TEAM_MEMBERSTool to search for team members by email address or user ID. Use this to find users when assigning permissions or managing team access. Requires Owner or Admin role to execute.
Input parameters
Email address of the team member to search for. Use this to find users by their email.
User ID of the team member to search for. Use this to find users by their numeric ID.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_SUBMIT_MESSAGE_FEEDBACKTool to submit feedback (thumbs up/down) for a message in a CustomGPT conversation. Use this to record user satisfaction signals that help identify which AI responses are helpful and which need improvement. Feedback can be changed by submitting a new reaction value.
Input parameters
The unique identifier of the message to submit feedback for. Obtained from listing conversation messages.
The feedback reaction to record for this message. Use 'liked' for positive feedback, 'disliked' for negative feedback, or 'neutral' to clear existing feedback.
The ID of the agent (project) containing the message.
The session ID (UUID format) of the conversation containing the message. Obtained when creating or listing conversations.
Optional list of fields to expand in the response for additional insights.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_UPDATE_PAGE_METADATAUpdate document metadata for a specific page in a CustomGPT project. Updates custom metadata fields such as title, description, URL, and image that help organize and manage your knowledge base. Use when you need to add tags, categories, or other organizational information to documents.
Input parameters
The url of the document used in citations. Maximum 2000 characters.
The url of the image used in citations. Maximum 2000 characters.
The title of the document used in citations. Maximum 255 characters.
The id of a page in which metadata will be updated.
The id of an agent (formerly known as project) in which page is stored. Obtain this from the List Projects action.
The description of the document used in citations. Maximum 500 characters. Should be one to two sentences.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_UPDATE_PROJECTUpdates an existing CustomGPT agent's name or configuration settings. Use this to rename an agent or modify its basic properties without affecting its knowledge base. Returns the complete updated project details including all metadata.
Input parameters
Whether the agent is public or not. Set to true to make the agent publicly accessible.
The unique identifier of the agent (formerly known as project) to update.
Agent name to update. Use this to rename the agent.
Sitemap path for the agent. Provide a URL to a sitemap XML file.
Whether the agent should anonymize user data. Set to true to enable data anonymization.
Whether OCR (Optical Character Recognition) is enabled for document processing.
Whether to retain file data after processing. Set to true to keep uploaded files.
Whether project licenses are allowed. Set to true to enable license management for this agent.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_UPDATE_PROJECT_LICENSEUpdates the name of an existing license for a CustomGPT project/agent. Prerequisites: - The project must have licenses enabled in its plan - Both project ID and license ID must be valid and exist - Use List Projects to get valid project IDs - Use List Project Licenses to get valid license IDs for a project This action only updates the license name. Other license properties cannot be modified through this endpoint.
Input parameters
The new name to assign to the license (1-255 characters recommended)
Unique identifier of the license to update. Obtain this from the List Project Licenses action.
Numeric ID of the CustomGPT project/agent (as string). Obtain this from the List Projects action.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_UPDATE_PROJECT_SETTINGSUpdate CustomGPT agent configuration settings. Updates persona instructions, response format, citation style, branding, and deployment settings. Only include fields you want to change - omitted fields retain their current values. Use this to configure agent behavior, customize appearance, or adjust user experience settings.
Input parameters
The unique identifier of the agent/project whose settings to update
Background image file for the agent widget.
Font family options for the agent.
User avatar image file.
Primary color for the agent in hex format (e.g., '#000000')
AI models available for the agent.
Title displayed for the agent
Text for 'view less' button in starter questions
Text for 'view more' button in starter questions
Default prompt or welcome message shown to users
Text appended to every agent response
Radius styling options for the agent.
Whether agent is aware of logged-in user's name
Avatar image file for the agent.
Whether to remove CustomGPT branding from the agent
Response source configuration options.
Agent capability levels for processing user queries.
Background type for the agent widget.
Language codes for agent interface messages.
Citation display setting (0-3 scale)
Whether to show thumbs up/down feedback buttons
Whether to enable enhanced search for numeric codes (may slow responses)
Whether to enable Markdown formatting in responses
Spotlight avatar image file.
Background color in hex format (e.g., '#FFFFFF')
List of example questions to guide users
Message shown while agent is processing a response
Message shown when agent cannot answer a question
Message shown when the agent encounters an error
Whether agent monetization is enabled
Color for the agent title in hex format
Citation display control options.
Whether to enable user avatar display
Additional text for input field (e.g., Terms of Service URL)
System instructions defining agent personality and behavior
Whether to show avatar next to title
Color scheme options for the agent.
Color for the agent toolbar in hex format
Spotlight avatar type options.
Whether users can share conversations
Image citation display options.
Spotlight avatar shape options.
Whether users can export conversations
Avatar orientation options.
Conversation activity window: 0=24hr memory limit, 1=unlimited, 2=close after 24hrs
Whether to enable spotlight avatar display
Message encouraging users to ask example questions
Label text for the sources section
Custom retention period in days for conversations (used when retention_period is 'custom')
Whether citations appear inline within responses
Whether to hide source names in agent responses
Whether to limit the height of image citations
Agent title and avatar alignment options.
Whether to show loading animation while waiting for response
Whether to use OpenGraph images from source pages in citations
Message shown when content fails moderation checks
Conversation retention period options.
Label text for the answer source indicator
Whether to generate context-aware starter questions
Whether to use reCAPTCHA for public agent access
Whether agent is aware of its knowledge base scope
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_UPDATE_SOURCEUpdate source settings for a CustomGPT agent data source. Configure how the source is indexed and kept up to date by adjusting auto-sync frequency, crawl depth, file filters, and refresh behavior. Use this to fine-tune sitemap crawling (JavaScript execution, image extraction), control which pages are added or removed during syncs, and set up custom refresh schedules.
Input parameters
The unique identifier of the data source to update.
The unique identifier of the agent (formerly known as project).
Whether the agent source should execute JavaScript when crawling web pages.
Add new pages to agent automatically during refresh agent source.
Custom schedule configuration for advanced data refresh frequency.
Allow extra timeout for agent source during crawling operations.
Remove pages from agent automatically during refresh agent source if they no longer exist.
Method used for extracting images from the website.
Data refresh frequency options for source auto-sync.
Options for refreshing existing pages during source sync.
Whether to update existing images during refresh operations.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_UPDATE_USER_PROFILEUpdates the authenticated user's profile information in CustomGPT. Use this action to modify profile details such as the user's display name, email address, or profile photo URL. All fields are optional - only the fields you provide will be updated. The action returns the complete updated user profile.
Input parameters
The user's full display name. Can include special characters and Unicode.
The user's email address for account identification and notifications.
URL pointing to the user's profile photo. Note: CustomGPT may auto-generate profile photos based on initials instead of using custom URLs.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CUSTOMGPT_VERIFY_MESSAGETool to verify message accuracy by triggering a fact-checking verification process. Use when you need to verify claims in a conversation message against source documents. The system compares each claim and reports which claims are supported, partially supported, or unsupported.
Input parameters
The message ID of the message to verify.
The ID of the agent (project) to verify the message for.
The session ID of the conversation containing the message to verify.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
No publicly available marketplace agent is found using this tool yet. There are 90 agents privately built on Nagent that already use Customgpt.
Build on Nagent
Connect Customgpt to any Nagent agent in minutes — no API key management, no boilerplate. Just configure and deploy.
The five questions agent builders ask before adopting a new integration.
Open the External Integrations panel inside Nagent (app.nagent.ai/externalIntegration), find Customgpt, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, Customgpt is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once Customgpt is connected, you configure its 40 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop Customgpt steps into any workflow visually. Pick an action (e.g., one of those listed above), fill in the inputs (Helix knows the required vs. optional schema for each parameter), and connect it to upstream/downstream steps. Triggers run as the entry point of an agent, so when a Customgpt event fires, the agent kicks off automatically.
Every Customgpt action and trigger ships with a fully-typed schema — input parameters with name, type, required flag, and description, plus the output payload shape. The schemas are documented in the sections above. Helix uses these schemas to validate your configuration at build time and to type-check the data flowing between steps.
Yes. While Customgpt ships with 40 pre-built ai chatbots actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching Customgpt together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build Customgpt-based workflows tailored to your business.