V3.23.0904 (2025-09-04)

Workspace

• Market officially launches WorkPilot - Microsoft Word Add-in. This extends the power of GPTBots Agent into Word documents, enabling employees to seamlessly leverage Agent capabilities and boost productivity.
  • WorkPilot supports Office Word enterprise accounts (Mac OS, Windows).
  • Organization administrators can configure the Agent skills to be extended into Word under Workspace → Space Management.

V3.22.0904 (2025-09-04)

Workspace

1. Workspace is now formally separated from the AI Agent Development Space
   • Workspace: Enterprise employees can use company-published Agents, workflows, AI Search and Market AI applications here to improve their work and business efficiency.
   • DevSpace: Enterprise AI developers can build, debug, deploy, publish and maintain AI applications (Agents, workflows, Tools) here to enhance AI development efficiency.
2. Introducing AI Search - enterprise employees can now use AI Search in the workspace, with support for custom models, system prompts and Tools, as well as uploading images, audio, documents and other materials
3. Agent has been restructured to optimize interaction experience and functionality, with new support for managing history records and improved interaction experience for favorites, applications, conversations and other features
4. Introducing Workflow - enterprise employees can use Workflow functionality to submit data via form options and obtain structured execution results, while managing execution records.
5. Launching Market feature in Workspace - will continue to roll out diverse AI applications to meet various enterprise needs.
6. Added Space Management to Workspace - enterprise administrators can manage employee usage permissions, application permissions, credit consumption and member management in the workspace.
   • Space Usage: Supports enterprise viewing of workspace AI applications, members, credit consumption, usage statistics and other data
   • Review & Publish: Supports enterprise administrators reviewing Agents and workflows published from the Development Space to ensure application quality and security. After approval, enterprise employees can view and use them in the Workspace.
   • Member Permissions: Workspace member permissions are now independent from Development Space - administrators can invite enterprise employees to join workspace and grant different feature usage permissions and credit quotas.
   • Market Management: Supports management of AI applications in Market - administrators can enable/disable AI applications and customize extension capabilities.
   • Space Settings: Supports enterprise administrators customizing workspace theme colors and integrating workspace H5 into enterprise apps, allowing employees to seamlessly use workspace AI applications within the app.

Agent Integration

• Integration Channel - Telegram Direct Messages: Supports Agent configuring multiple TG Bots simultaneously to respond to user messages from multiple TG Bots.
• Integration Channel - Telegram Group Chat: Supports Agent actively monitoring (full monitoring) multiple TG Bot group chats. The system will filter group messages based on monitoring frequency and rules (keyword matching or semantic matching), and submit matching messages to Agent for response.

V3.13.0827 (2025-08-27)

MultiAgent

• Launched the new MultiAgent feature, enabling you to build multi-agent systems where multiple agents collaborate to efficiently handle complex tasks.
• MultiAgent is currently in preview stage and we will continue to optimize and improve it. Note: Depending on task complexity, each run may consume significant credits. Please use judiciously.
• The MultiAgent system comes with several built-in professional system agent templates:
  • Plan Agent: Focuses on task decomposition and planning, creating clear execution plans.
  • Online Search Agent: Performs precise online searches and information retrieval, parsing webpage content to obtain external knowledge.
  • Coder IDE Agent: Professionally handles code generation tasks, transforming your requirements into high-quality code.
  • Computer Use Agent: Provides Linux system operation management, executing file management, system settings, and other tasks. Note: Current stability needs improvement, not recommended for production use.
  • Browser Use Agent: Provides browser operation management, executing webpage browsing, form filling, and other tasks. Note: Current stability needs improvement, not recommended for production use.

Workspace

• Workspace introduces the new Market feature, which will continue to roll out diverse AI applications to meet various enterprise needs.
• Market launches Live Speechly - an enterprise intelligent meeting assistant. It not only provides real-time meeting translation but also intelligently summarizes key points and automatically generates action plans, efficiently converting each meeting into actionable outcomes.
  • Live Speechly now supports Windows and MacOS systems.
  • Organization administrators can flexibly configure Live Speechly in "Workspace-Space Management" and select the most suitable voice translation model.
  • Organization administrators can also enable powerful extension features for Live Speechly: through setting trigger conditions and selecting different Agents, achieve intelligent meeting content summarization, mind map generation, automatic sales lead reporting to CRM, and automatic task todo creation.

Other Improvements

• Comprehensively optimized the Agent creation process for a smoother interaction experience
• Fixed multiple known issues to enhance system stability

V3.0.0818 (2025-08-18)

User API

• Released User Attributes Query API that enables precise user information retrieval via user_id and anonymous_id.

DataBase API

• Launched Data Table Batch Delete API for efficient deletion of table row data.
• Enhanced Data Table Status Query API with more detailed error feedback to help developers quickly identify and resolve issues.
• Upgraded Data Update API to V2, supporting batch data updates, automatic creation of new data entries, and comprehensive error feedback.

Audio File Optimization

• Added support for parallel batch transcription when uploading .WAV audio files to improve processing efficiency.

V3.0.0805 (2025-08-05)

Data Center

• Starting from V3.0.0805, GPTBots now allows enterprises to select different data centers for their organizations based on business requirements during organization creation.
• After organization creation, the data center cannot be modified. All resources under the organization (including agents, knowledge bases, databases, workflows, logs, etc.) will be stored in the selected data center to comply with local data regulations.
• API endpoint rules need to be adjusted according to the data center, with different data centers having different API endpoint patterns.
• Currently supported data centers are listed below, with GPTBots planning to gradually enable and support data centers in more countries/regions:
  • Singapore (Default): api-sg.gptbots.ai
  • Thailand: api-th.gptbots.ai

Agent - Insights

• Added a first-byte response time analysis chart for first-round conversations, visualizing the distribution of initial response latency when agents first engage with users.
• Integration-Bubble: Bubble ICON now supports Extra Large (96*96PX) size icons.

Workflow

• HTTP Request Node: Supports defining Path parameters using {} in URLs, e.g., https://api.example.com/{id}. Parameters can be either Query (default) or Path type
• End Node: Added JSON import functionality that automatically recognizes structure and populates key names and field types.
• Agent Configuration-Workflow: Added support for displaying workflow version information.
• Share: Enhanced workflow interface and interaction experience with keyboard shortcut support.

07-22

Agent Integration

• Added Intercom integration channel, enabling users to interact directly with Agents through Intercom.
• Added SaleSmartly integration channel, allowing users to communicate directly with Agents via SaleSmartly.
• LINE integration channel now supports configuring multiple LINE Channels simultaneously, enabling Agents to respond to user messages from multiple LINE Channels concurrently. GPTBots Assistant also provides support for LINE Channel integration.

07-16

SSO Login

• Added support for administrators to enable SSO (Single Sign-On) for organizations through SAML 2.0 protocol configuration.
• Support configuring multiple SSO login protocols for a single organization, and multiple organizations can simultaneously use the same SSO login protocol.
• Added organization list feature to view all organizations, including organization ID, name, creation time, member count, and more.

Workflow

• Workflows in integration channels now support sharing capabilities. Users can complete input on the web page and click "Run" to obtain workflow execution results.

Knowledge Base

• Google Drive integration now supports recognition, retrieval, and parsing of both Google Sheets and Google Docs online document formats.

06-18

Moderation

A new "Moderation” feature has been added. It can perform content review of the inputs to and outputs from the intelligent agent, ensuring that the outputs comply with ethical standards and legal regulations. Currently, the following content moderation models are supported:

• OpenAI Moderation: A content moderation model developed by OpenAI, which can be used to review text or images. The review scope includes areas such as sex, suicide, illegal activities, crimes, harm, discrimination, and more.

More content moderation models will be integrated gradually...

Additionally, the “Moderation” feature supports the following methods:

1. Custom API Extension: If you need to use models provided by other content moderation providers, you can connect via API interface. However, the API must conform to the specifications defined by GPTBots. Please refer to the documentation for details.

2. Keywords: A content review capability based on keyword matching, where a matching keyword is considered a hit. This is the most traditional method of content moderation.

Data Anonymization

A new “Data Anonymization” feature has been added. It can anonymize users’ privacy information (PII) in the inputs before submitting them to the intelligent agent for processing. This helps effectively enhance the protection of privacy information.

06-05

Workflow

• Support defining component input parameter variable types.
• Start: Support importing input parameters in JSON format.
• LLM: Support importing input parameters in JSON format.
• HTTP Request: Support importing complete HTTP request configuration in cURL format.
• Added "Tool" component: Support adding self-built tools or GPTBots official tools as workflow nodes.
• Added "File Parser" component: Support parsing file-type variables into text output.
• Added "Text Processor" component: Support processing text (strings), such as concatenation, splitting, etc.
• Added "Variable Aggregator" component: Support aggregating different variables from multiple branches into one variable for easier use in subsequent processes.
• Added "Log" module: View workflow execution logs for troubleshooting.
• Added "Insights" module: Monitor workflow operation status through visual dashboards, including metrics such as runs, errors, success rates, etc.

Message Input Box

• Agent now supports clipboard image data, allowing direct pasting of images as attachments.
• FlowAgent and Workflow canvas now support Undo operations via Ctrl+Z shortcut, with a maximum of 50 steps that can be undone.

05-28

Chrome Extension

GPTBots Assistant is a Chrome browser extension built for GPTBots platform agents. After configuring the Agent's APIKey, it enables features like Human Handoff Notifications and Reply Suggestions.

The current version's Reply Suggestions feature supports the LINE platform, while Human Handoff Notifications are supported across all platforms in the integration module. For detailed information and extension download, please refer to GPTBots Assistant.

05-12

LLM Updates

• Added support for the Gemini-2.0-Flash-Image-Generation model, enabling LLMs to generate single or multiple images.
• Exposed advanced LLM parameter controls, allowing users to customize model-supported parameters such as Temperature, Top P, Top A, Top K, Presence Penalty, Frequency Penalty, Repetition Penalty, Min P, and more.

Agent Message Type Enhancements

GPTBots Agent now supports six types of input and output message formats: Text, Image, Audio, Video, Document, and File, making interactions with agents more flexible. The types of messages an agent can receive depend on the "Input-Attachment" configuration, while the types it can output depend on the capabilities of the underlying LLM.

Note: Supported formats for Image, Audio, Video, and Document messages may vary depending on whether "System Recognition" or "LLM Recognition" is selected.

FlowAgent Improvements

• Comprehensive optimization of the FlowAgent canvas creation experience, aligning interaction logic with workflow design.
• Added support for "Add Note" functionality, allowing users to annotate the canvas to help others understand the design and usage.
• Added the ability to insert new components in the middle of connection lines, enabling more flexible canvas design.
• Improved the component Prompt configuration UI for better clarity and ease of use.

Variable Reference

• Agents now support variable referencing in configurations (prompts, Flow components, welcome messages, etc.), including Global Variables, User Attributes, Browser Attributes, and Third-Party Platform Variables, enhancing agent flexibility and extensibility.
• Added a new global variable {{sys_user_msg_count}} to track the total number of messages exchanged between the user and the agent in the current conversation.
• FlowAgent now supports referencing Upstream Component variables in addition to the above, further improving flexibility and extensibility in FlowAgent configurations.

Zoho Sales IQ Integration

• Added integration support for the Zoho Sales IQ platform, allowing agents to be embedded in Zoho Sales IQ so users can interact with AI Agents directly through Zoho Sales IQ.
• Added support for Zoho Sales IQ in human handoff scenarios, supporting both Other to Zoho Sales IQ and Zoho Sales IQ to Zoho Sales IQ modes. After a user initiates a human service request, issues can be forwarded to Zoho Sales IQ customer service for resolution.

Knowledge Base QA Enhancements

• Knowledge Base QA now supports importing .xlsx and .xls files.
• Google Drive integration now allows users to select .csv, .xlsx, and .xls files for QA data import via the "Template Import" feature. Updates and management of spreadsheets in Google Drive are automatically synchronized to the AI Agent in GPTBots.

04-22

AI Agent knowledge source display

• Display knowledge documents and tool calls simultaneously
• Tag mode, incorporating knowledge source localization, allowing single-click tracking to the specific location of referenced knowledge in the original document
• Support for viewing the full text of referenced documents

Knowledge base slicing optimization

• Optimized knowledge base slicing display logic to enhance readability
• PDF, table, and docx documents now support locating the corresponding position in the original document and highlighting the corresponding section by selecting slices

Knowledge base upload - Tables

• A "custom row split" function has been added for table-type files, allowing users to split according to specified row numbers

Agent integration

• Support for the LINE platform, enabling the reception and recognition of user-sent messages, including text, images, audio, and documents

Log

• In Logs-Conversation, provides support for viewing user attribute information, including user ID, anonymous ID, email, and phone number

04-10

Newly developed Workflow module

Build intelligent workflows for AI applications through a simple drag-and-drop operation on a canvas. Your workflows can either be integrated into AI agents as tools, or serve as standalone APIs for seamless integration with any external program or system.

Feature optimization

• Upgraded all integration channels to V2 API, supporting conversation interruption mode.
• The model service protocol now supports OpenRouter services, enhancing LLM service stability.
• Voice message now supports 90s duration.
• Added support for automatic capture of message timestamps, enhancing LLM's temporal awareness during interactions.

03-28

• Supports customizing "Receive message type" in "Human handoff" for both Agent and FlowAgent.
• Supports setting "Receive message type" seperately for AI Agent interaction and Human handoff interaction.

03-26

• Variable usage: Supports the use of system predefined variables in agent configurations (prompts, Flow components, welcome messages, etc.), including global attributes (conversation ID, user ID, etc.), browser attributes (browser name, time zone, etc.), and third-party application attributes (WhatsApp, Telegram, and LiveChat client-related attributes, such as user ID, conversation ID, etc.). This helps maximize the agent's capabilities in different scenarios.

03-21

• When entering live chat for manual service through the Bubble Widget, users are allowed to send and receive text messages, audio messages, image messages, and document messages.
• The Bubble Widget supports uploading customized images to showcase the company's branding or background within the chat interface.

03-17

• Knowledge base/database supports global and knowledge base-level granularity permission configuration, improving data permission management efficiency.
• Optimized the display logic of knowledge base ID and data table ID.
• Inference models allow custom settings for reasoning depth and control over the display of the inference process, enhancing the interaction effects of the displayed content.
• The Webhook V2 version of the Dialogue - Send Message V2 API has been released, supporting audio messages, text messages, and detailed data on points and token consumption.

02-28

• The human service function module supports customizable prompt messages and multi-language configuration. The front end automatically adapts the display information based on the browser language.
• Optimized the bubble avatar display to a circular shape.
• Supports OpenAI project key authentication scheme.
• Released AI Agent Dialogue API V2, supporting text, audio, image, and document message types, including token and credit consumption details.
• Integration: Enables the agent to be integrated into Facebook Messenger and Instagram. Facebook and Instagram users can seamlessly interact with the agent through text, images, and voice.
• Supports OpenAI GPT 4.5 version & Anthropic Claude Sonnet 3.7 version.

02-17

• Support OpenAI Audio LLM, allowing users to input voice and directly reply with voice messages, eliminating the need for ASR and TTS.
• Text and voice conversations now support an "interruptible conversation mode," allowing users to send multiple messages in a short time while receiving a single response message, enhancing the user experience.

01-09

Agent Insights

Insights: H

• Real-time: Agent usage for the current day.
• Effectiveness: Metrics related to issue resolution effectiveness, manual intervention, user sentiment analysis, etc.
• Usage: Usage of credits and tokens.
• Users: Metrics such as user count, new users, active users, etc.
• Behavior: Metrics related to conversations, interactions, etc.
• Health: Metrics such as response speed, errors, and requests per minute.