> ## Documentation Index > Fetch the complete documentation index at: https://docs.cognigy.com/llms.txt > Use this file to discover all available pages before exploring further. # Manage AI Agents Updated in 2026.6 To manage a new generation of AI Agents, Cognigy.AI introduces the *AI Agent Management* interface, where you can create, edit, and delete AI Agents. ## Create AI Agents You can create an AI Agent from scratch or hire an AI Agent from the Job Market, designed for your industry, such as airlines, food services, or sales, and customize it to fit your business needs. To create an AI Agent, select one of the following options: * [Create from scratch](#create-from-scratch) * [Hire from the Job Market](#hire-from-the-job-market) ### Create from Scratch 1. In the left-side menu of the **Project** page, select **Build > AI Agents**. 2. Click **Create AI Agent** if you are creating an AI Agent for the first time, or click **+ New AI Agent** on the **AI Agents** page if you have created at least one AI Agent before. Configure the following settings: 1) In the **General Settings** step, fill in the following fields: * **Name** — enter a name for your AI Agent. This name will be visible to end users when the AI Agent greets them in the chat or when one AI Agent transfers the conversation to another AI Agent. For example, `Hello, my name is Sara. How can I help you?` or `Our support specialist Alex will help with this question, transferring the conversation now`. * **Description** — enter a description of the AI Agent that shapes its behavior and enhances its ability to understand the desired communication style. For example, describe the AI Agent as follows: `Anna works at ACME and is highly skilled at making customers feel comfortable.` 2) In the **Avatar** section, select avatar of your choice or upload your custom one by clicking **+** next to avatars. You can use any image as an avatar for your AI Agent, or create a Cognigy-style avatar using the [Cognigy.AI PSD template](https://docscognigyassets.blob.core.windows.net/assets/Template.psd). To open and customize the template, you will need Adobe Photoshop or [Paint.net](https://www.getpaint.net/) with the [PSD plugin](https://www.psdplugin.com/) installed. The requirements for the avatar are as follows: * Use an alpha channel for a transparent background. * Set the recommended width to 136px. * Set the recommended height to 184px. * Save the file as `.png`. * Include `_optimized` in the file name. 1. In the **Speaking Style** step, configure the following settings: * **Set up Style** — configure how the AI Agent's choice of wording is influenced by the selected speaking style, which can affect the tone and clarity of its responses: * **Concise/Comprehensive** — adjust the slider to the left for brief responses and to the right for detailed responses. * **Formal/Informal** — adjust the slider to the left for more casual and conversational responses, and to the right for professional and structured responses. * **Voice Configuration** — assign a specific voice to your AI Agent if you want to use your AI Agent as a voice-based assistant. To configure this setting, ensure you have installed [Voice Gateway](/voice-gateway/index) and set up the [Voice Preview](/ai/agents/test/voice-preview) provider. Then, fill in the fields following the same process you used for [Set Session Config Node](/ai/agents/develop/node-reference/voice/voice-gateway/parameter-details): * **TTS Vendor** — select the text-to-speech provider for your AI Agent. This setting determines which service will convert the AI Agent's text responses into speech. * **TTS Language** — select the language that your AI Agent will use for speech output. Ensure this language aligns with the preferred language of the end user. * **TTS Voice** — select the voice from the selected TTS vendor. This setting allows you to customize the tone, gender, and style of your AI Agent's voice. * **TTS Label** — select the alternative name of the TTS vendor, as specified in the [Voice Gateway Self-Service Portal](/voice-gateway/webapp/applications#add-additional-tts-and-stt-vendor). If you have multiple speech services from the same vendor, use the label to specify which service to use. * **Disable TTS Audio Caching** — by default, this setting is deactivated. With caching enabled, previously requested TTS audio is stored in the AI Agent cache, and repeated requests for the same audio text will use the cached result instead of sending another request. With caching disabled, the AI Agent stores the TTS audio but doesn't use it; each request is sent directly to the speech provider. Note that disabling caching can increase TTS costs. For detailed information, contact your speech provider. * **Language Configuration** — by default, this setting is activated. Deactivate automatic language detection to ensure the AI Agent always responds in the language defined by your instructions. This setting provides predictable and consistent responses, preventing unintended language switching when users say or type words from more than one language. When active, this setting also simplifies the system prompt, giving you clearer control over language behavior. 1. In the **Instructions** step, configure the following setting: * **Instructions** — provide special instructions to your AI Agent in bullet-point form. For example: ```txt theme={null} - Greet users warmly and professionally. - Keep responses concise; expand only if requested. - Start with a formal tone; adjust as needed. - Share troubleshooting links for technical issues. - Apologize if errors occur, then correct promptly. ``` 1. In the **Knowledge Store** step, configure the following settings: * **Knowledge Store Type** — select or upload a knowledge source that the AI Agent will use to access information from the documents you provide. By accessing and understanding these knowledge bases, the AI Agent can deliver more accurate, context-aware, and helpful responses to user queries. You need to configure an [embedding model](/ai/agents/develop/knowledge-ai/overview) to use Knowledge AI. Select one of the following options: * **Choose existing Knowledge Store** — select the [Knowledge Store](/ai/agents/develop/knowledge-ai/knowledge-store) that the AI Agent will use to access information from the documents you provide. * **Upload Knowledge Source** — upload documents with supported formats, such as PDF, text, DOCX, PPTX, or CTXT file formats. The CTXT file format has restrictions. For more information, refer to the [CTXT](/ai/agents/develop/knowledge-ai/knowledge-source/text-formats/ctxt) article. * **Upload URL Knowledge Source** — enter the URL of the web page to be used as a Knowledge Source. This type of Knowledge Source has restrictions. For more information, refer to the [Web Page](/ai/agents/develop/knowledge-ai/knowledge-source/text-formats/web-page) article. 1. In the **Data Privacy & Security** step, configure the following fields: * **Contact Profile Information** — select which information the AI Agent should use from the [Cognigy Contact Profile](/ai/agents/analyze/contact-profiles): * **None** — no data will be used from the Contact Profile. This option is selected by default. * **Selected Profile Fields** — enter specific fields from the Contact Profile for targeted data use. Specify the field using the [Profile keys](/ai/agents/analyze/contact-profiles#profile-schema) format and press Enter to apply it. * **Complete Profile** — use all fields from the Contact Profile to provide comprehensive user details. * **Profile Memories** — use the [Memories](/ai/agents/analyze/contact-profiles#profile-schema) field from the Contact Profile. * **Safety Instructions** — adjust the AI Agent's safety settings to guide content generation, interactions, and responses, ensuring compliance with ethical, legal, and operational standards. Although these settings reduce risks, occasional unexpected outputs may still occur. The selected safety instructions are included in the prompt to enhance safety, which may increase token usage. Select the safety instructions you want to apply: * **Avoid harmful content** — prevent generating content that could be harmful, offensive, or abusive to end users. * **Avoid ungrounded content** — prevent generating content that is based on speculation or unsupported claims, ensuring it is reliable and verifiable. * **Avoid copyright infringements** — prevent generating content that violates intellectual property rights or uses copyrighted material without authorization. * **Prevent jailbreak and manipulations** — prevent attempts to bypass security measures or manipulate the AI Agent into producing unauthorized or unsafe content. 1. In the **Job Selection** step, select one of the following options: * **Default** — create an AI Agent with a predefined Flow, then click **Create & Configure LLM** to save changes and open the Flow with the created AI Agent. If you haven't added an LLM before, the system will prompt you to [configure a model](/ai/agents/overview#prerequisites) to ensure your AI-driven Flow works. * **Personality Only** — create an AI Agent without a predefined Flow, then click **Create** to save changes. * **Job** — select one of the available jobs you want to assign to the AI Agent, then click **Create** to save changes. You can create an Agent from scratch using the [Cognigy.AI API POST beta/aiagents](https://api-trial.cognigy.ai/openapi#post-/beta/aiagents) request. ### Hire from the Job Market 1. In the left-side menu on the **Project** page, select **Build > AI Agents**. 2. On the **AI Agents** page, click **Hire AI Agent**. The **Job Market** page displays a list of available AI Agents to hire. 3. Hover your cursor over the desired AI Agent template and click **Hire**. This action will trigger the **Hire AI Agent** task in the Task Manager. 4. Check the status of the **Hire AI Agent** task by clicking task-menu in the upper-right corner. 5. Once the task is complete, go to **Build > Flows** and find the Flow with the AI Agent name from the template you installed. You can hire an Agent from the Job Market using the [Cognigy.AI API POST beta/aiagents/hire](https://api-trial.cognigy.ai/openapi#post-/beta/aiagents/hire) request. ## Combine Custom and Hired AI Agents You can reassign your custom AI Agent to take on the responsibilities of the hired AI Agent. To do this, hire an AI Agent from the Job Market and configure their interaction by defining which functions and personality traits should be combined. This approach lets you combine the strengths of both AI Agents: ready-made job functions from the hired AI Agent and your brand's AI Agent persona from your custom AI Agent. To combine custom and hired AI Agents, follow these steps: 1. On the **AI Agents** page, select **+ Hire AI Agent**. The **Job Market** page displays a list of available AI Agents to hire. 2. Hover your cursor over the desired AI Agent template and click expand **> Hire & Configure**. 3. In the **Select an AI Agent to Combine** window, use the search field to find an AI Agent by name, then select the AI Agent from the list. 4. Click **Combine**. This action will trigger the **Hire AI Agent** and **Merge Package** tasks in the Task Manager. 5. In the left-side menu of the **Project** page, select **Build > Flows**. 6. Select the Flow that belongs to the hired AI Agent. In the Flow, you will see an AI Agent Node with your custom AI Agent persona. ## Configure Jobs and Tools for AI Agents When you create an AI Agent from scratch or add one from the Job Market, you can add or change jobs and tools in the AI Agent configuration. 1. Open the created AI Agent and go to the **Jobs** tab. 2. Fill in the following fields: * **Job Name** — enter a title for the job you want to assign to the AI Agent. For example, `Customer Support Specialist`. * **Job Description** — enter a description of the job that outlines the responsibilities and tasks associated with the role. For example, `Handle customer inquiries, provide product information, and resolve issues efficiently`. * **Instructions and Context** — provide specific instructions or guidelines that the AI Agent should follow while performing its job. For example, `Always respond politely, escalate complex issues to a human agent, and ensure customer satisfaction`. ### Configure Tools for AI Agents In the **Tools** section, click **Add Tool** to add tools that the AI Agent can use to perform its job. Select one of the following options: A tool is a specific task that an AI Agent can perform. The AI Agent can call tools to perform different tasks, such as retrieving information from a database or interacting with an external API. Fill in the following fields: | Parameter | Type | Description | | ----------- | ------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------- | | Tool ID | CognigyScript | Provide a meaningful name as a tool ID. This ID can contain only letters, numbers, underscores (`_`), or dashes (`-`). For example, `update_user-1`. | | Description | CognigyScript | Provide a detailed description of what the tool does, when it should be used, and its parameters. | Configure the parameters that will be collected by the AI Agent before the tool is called. You can switch between the Graphical and JSON editors. When editing the JSON, follow the [JSON Schema specification](https://json-schema.org). | Parameter | Type | Description | | --------------- | -------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Use Parameters | Toggle | Activate this toggle to add parameters in addition to the tool name and description. The AI Agent will collect all data it needs and call a Tool with these parameters filled as arguments. These values can be accessed directly in the `input.aiAgent.toolArgs` object. | | Name | Text | Specify the name of the parameter. The name should be clear and concise, and describe the purpose of the parameter. | | Type | Selector | Select a type of the parameter:
  • **String** — a sequence of characters. For example, `"hello"`, `"123"`.
  • **Number** — a numerical value, which can be either an integer (for example, `5`) or a floating point number (for example, `3.14`).
  • **Boolean** — a logical value representing `true` or `false`.
  • **Array** — a collection of elements, which can contain multiple values of any type. For example, `["apple", "banana", "cherry"]`.
  • **Object** — a collection of key-value pairs, where each key is a string and the value can be of any type. For example, `{"name": "John", "age": 30}`.
| | Description | Text | Explain what the parameter means by providing a brief description of the parameter's usage. | | Enum (optional) | Enum | Define a set of values that the parameter can accept. The enum restricts the input to one of the specified values, ensuring only valid options are chosen. The enum is only available for string-type parameters in the Graphical editor. For other types, use the JSON editor. May not be supported by all LLM providers. | | Add Parameter | Button | Add a new parameter. | | Parameter | Type | Description | | ------------------------- | ------ | ----------------------------------------------------------------------------------------------------------------- | | Debug Message when called | Toggle | Enable the output of a debug message when the tool is called to provide detailed information about the tool call. | | Parameter | Type | Description | | --------- | ------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Condition | CognigyScript | The tool will be enabled only if the condition is evaluated as true. If false, the tool isn't part of the AI Agent's Tools within this execution. For example, when using the `unlock_account` tool, you can specify a condition like `context.accountStatus === "locked"`. This checks the value in the context, and if it is missing or different, the tool will not be enabled. | An MCP tool connects to a remote [MCP server](https://modelcontextprotocol.io/introduction) to load tools that the AI Agent can execute. Fill in the following fields: | Parameter | Type | Description | | ------------------ | ------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Name | CognigyScript | Provide a name for the MCP connection. This name helps you identify the source of the loaded tool. | | MCP Server SSE URL | CognigyScript | Provide the URL to an SSE (Server-Sent Events) endpoint from a remote [MCP server](https://modelcontextprotocol.io/introduction). Ensure that you connect only to trusted MCP servers. | | Timeout | Slider | Set the timeout time for the MCP connection in seconds. | | Parameter | Type | Description | | ------------------- | -------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Authentication Type | Selector | The authentication type to use for the MCP server connection. Select one of the following options:
  • **None** — no authentication. This option is used by default.
  • **OAuth2** — authenticate using OAuth 2.0, which provides improved security and control compared to API keys. OAuth 2.0 supports scoped permissions, expiring tokens, and reduced exposure through short-lived tokens.
If you want to use a different authentication method, such as an API key, you can add it as a custom header in **Custom Headers** of the **Advanced** section. | | OAuth2 Parameters | Selector | Opens the fields required to configure OAuth 2.0 authentication. These fields allow the AI Agent to securely request and use access tokens when communicating with the MCP server. Configure the following fields:
  • **Connection Name** — enter a descriptive name for the connection, for example, `MCP Tool OAuth`.
  • **OAuth URL** — enter the token endpoint URL exposed by the MCP server, for example: `https://mcp.example.com/oauth2/token`.
  • **Client ID** — enter the application (client) ID issued by the MCP server.
  • **Client Secret** — enter the application secret issued by the MCP server. Keep it secure.
  • **Scope** — add a list of scopes that define the permissions required by your application, for example: `read write admin`. Separate multiple scopes with spaces.
| | Parameter | Type | Description | | --------------------- | ------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Debug Loaded Tools | Toggle | Enable this parameter to display a debug message listing all tools loaded from the MCP server. The debug message also includes tools filtered out in the Advanced section. This parameter shows whether tools were loaded from the cache or directly from the MCP server. | | Debug with Parameters | Toggle | Enable this parameter to include the Tool Parameters in the debug message. | | Debug calling Tool | Toggle | Enable the output of a debug message when the tool is called to provide detailed information about the tool call. | | Parameter | Type | Description | | -------------- | ------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Cache Tools | Toggle | Disables caching of loaded tools while developing. Ensure that caching is enabled in production for performance reasons. The caching time is 10 minutes. In debug mode, you can verify whether the cache was used. To do this, make sure **Debug Loaded Tools** is enabled. For more information, see the [Debug Settings](#debug-settings) section. | | Condition | CognigyScript | Sets the condition under which the tool will be activated. If the condition is evaluated as false, the tool isn't part of the AI Agent's Tools during execution. For example, when using the `unlock_account` tool, you can specify a condition like `context.accountStatus === "locked"`. This checks the value in the context, and if it is missing or different, the tool will not be enabled. | | Tool Filter | Selector | Controls if tools should be excluded from execution. You can select one of the following options:
  • **None** — no tool filtering is applied, and all tools are available for execution. This option is selected by default.
  • **Whitelist** — only tools on the list are allowed for execution, while all other tools are excluded.
  • **Blacklist** — tools on the list are excluded from execution, while all other tools remain available.
| | Blacklist | CognigyScript | The parameter appears if you select **Blacklist** in **Tool Filter**. Specify the tools that should be blocked from execution. Specify only one tool per field. | | Whitelist | CognigyScript | This parameter appears if you select **Whitelist** in **Tool Filter**. Specify the tools you want to allow for execution. Specify only one tool per field. | | Custom Headers | - | Sets custom authentication headers to send with the request to the MCP server. Use the **Key** and **Value** fields to enter a header. The **Value** field supports CognigyScript. After entering the header key, new empty **Key** and **Value** fields are automatically added, in case you need to add more headers. Alternatively, you can click **Show JSON Editor** and enter the headers in the code field. | You can add multiple tools to the AI Agent. The recommended maximum number of tools is 20. The following video shows an MCP Tool example: