Skip to main content
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

  • GUI
  • API
  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. To open and customize the template, you will need Adobe Photoshop or Paint.net with the PSD plugin 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 and set up the Voice Preview provider. Then, fill in the fields following the same process you used for Set Session Config Node:
      • 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. 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.
  1. In the Instructions step, configure the following setting:
    • Instructions — provide special instructions to your AI Agent in bullet-point form. For example: 
       - 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 to use Knowledge AI. Select one of the following options:
      • Choose existing Knowledge Store — select the 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 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 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:
      • 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 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 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 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.

​
Hire from the Job Market

  • GUI
  • API
  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.

​
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:
  • Regular Tools
  • MCP Tools
A tool is a specific task that an AI Agent can perform. The AI Agent can call to perform different tasks, such as retrieving information from a database or interacting with an external API. Fill in the following fields:
ParameterTypeDescription
Tool IDCognigyScriptProvide a meaningful name as a Tool ID. This ID can contain only letters, numbers, underscores (_), or dashes (-). For example, update_user-1.
DescriptionCognigyScriptProvide 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.
ParameterTypeDescription
Use ParametersToggleActivate 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.
NameTextSpecify the name of the parameter. The name should be clear and concise, and describe the purpose of the parameter.
TypeSelectorSelect 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}.
DescriptionCognigyScriptExplain what parameter means by providing a brief description of the parameter’s usage.
Enum (optional)EnumDefine 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 ParameterButtonAdd a new parameter.
ParameterTypeDescription
Debug Message when calledToggleEnable the output of a debug message when the tool is called to provide detailed information about the tool call.
ParameterTypeDescription
ConditionCognigyScriptThe 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.

​
Configure AI Agent Settings for Each Job

Configure more settings for managing AI Agents:
ParameterTypeDescription
Long-Term Memory InjectionSelectorAllow the AI Agent to access Contact Profile information for the current user. Select one of the following options:
  • None – no memory.
  • Inherit from AI Agent – use the settings specified in the AI Agent creation settings.
  • Inject full Contact Profile – use all information from the Contact Profile.
  • Inject Contact Memories only – use information only from the Memories field in the Contact Profile.
  • Inject selected Profile fields – use information from specific fields in the Contact Profile.
Selected Profile FieldsTextThis parameter appears when the Inject selected Profile fields option is enabled. Enter specific fields from the Contact Profile for targeted data use. Specify the field using the Profile keys format and press Enter to apply it.
Short-Term Memory InjectionCognigyScriptSpecify a static string or a dynamic value via CognigyScript to make available to the AI Agent in the current turn.
ParameterTypeDescription
Knowledge InjectionSelectorUse the Knowledge AI feature for the AI Agent. Select one of the following options:
  • Never — do not use the Knowledge Stores.
  • When Required — let the AI Agent decide when querying the Knowledge Stores is required to help the user.
  • Once for Each User Input — query the Knowledge Store(s) after each user input. Note that executing a query on every user input can lead to increased costs and latency.
Use AI Agent KnowledgeToggleThe parameter appears when you select either When Required or Once for Each User Input. Enable to use the Knowledge Store configured in the AI Agent. The Knowledge Store configured within the AI Agent creation settings will be used.
Use Job KnowledgeToggleThe parameter appears when you select either When Required or Once for Each User Input. Enable this option to configure a specific Knowledge Store for this particular job, allowing the AI Agent to access job-specific data or resources.
Job Knowledge StoreSelectorThe parameter appears when you select either When Required or Once for Each User Input. The parameter appears when the Use Job Knowledge option is enabled. Select a specific Knowledge Store for this AI Agent’s job.
Top KSliderThe parameter appears when you select either When Required or Once for Each User Input. Specify how many knowledge chunks to return. Providing more results gives the AI Agent additional context, but it also increases noise and token usage.
Source TagsCognigyScriptThe parameter appears when you select either When Required or Once for Each User Input. The tags serve to refine the scope of your knowledge search, allowing you to include only the most pertinent sections of the knowledge base and, as a result, improve the accuracy of search outputs.Before specifying tags, ensure that they were provided during the creation of the Knowledge Sources. Add Tags by specifying each Tag separately and pressing ++enter++. The maximum number of tags is 5.When you specify multiple Source Tags, the Search Extract Output Node defaults to an AND operator, meaning it only considers Sources that have all the specified Tags. This approach ensures the search results are precise and highly relevant to the end user’s query. To change this behavior, go to the Match Types for Source Tags parameter.
Match type for Source TagsSelectThe parameter appears when you select either When Required or Once for Each User Input. The operator to filter Knowledge Sources by Source Tags. Select one of the following options:
  • AND — the default value, requires all tags to match across multiple Knowledge Sources. Consider the following example: there are Knowledge Sources with Tags S-a, S-b, and S-c. When you use the AND operator to filter by S-a and S-b, only Sources with both Tags S-a and S-b will be included in the search results.
  • OR — requires at least one tag to match across multiple Knowledge Sources. Consider the following example: there are Knowledge Sources with Tags S-a, S-b, and S-c. When you use the OR operator to filter by S-a or S-b, any Source with either Tag S-a or S-b will be included in the search results.
Generate Search PromptToggleThe parameter appears when you select Once for Each User Input. This parameter is enabled by default and allows you to generate a context-aware search prompt before executing the knowledge search. Note that enabling this parameter may lead to increased cost and latency.
ParameterTypeDescription
How to handle the resultSelectDetermine how to handle the prompt result:
  • Store in Input — stores the AI Agent result in the Input object. To print the prompt result, refer to the configured Context key in a Say Node or enable the Output result immediately option.
  • Store in Context — stores the result in the Context object. To print the prompt result, refer to the configured Context key in a Say Node or enable the Output result immediately option.
  • Stream to Output — streams the result directly into the output. This means that chunks coming from the prompt response will be output directly into the conversation chat as soon as a Stream Buffer Flush Token is matched, and you don’t need to use the AI Agent Output Token token and Say Node. By default, this result won’t be stored in either the Input or the Context. You can change this behavior by activating the Store Copy in Input option.
Input Key to store ResultCognigyScriptThe parameter appears when you select either Store in Input or Stream to Output. The result is stored in the input.aiAgentOutput object by default. You can specify another value, but the AI Agent Output Token will not work if the value is changed.
Context Key to store ResultCognigyScriptThe parameter appears when Store in Context is selected. The result is stored in the context.aiAgentOutput object by default. You can specify another key.
Stream Buffer Flush TokensText ArrayThe parameter appears when Stream to Output is selected. It defines tokens that trigger the stream buffer to flush to the output. The tokens can be punctuation marks or symbols, such as \n.
Output result immediatelyToggleThe parameter appears when you select either Store in Input or Store in Context. This parameter allows you to output results immediately without using the Say Node and AI Agent Output token.
Store Copy in InputToggleThe parameter appears when Stream to Output is selected. In addition to streaming the result to the output, store a copy in the Input object by specifying a value in the Input Key to store Result field.
ParameterTypeDescription
Voice SettingSelectConfigure the voice settings for the AI Agent Job. This parameter determines how the AI Agent selects the voice for text-to-speech (TTS) output. Select one of the following options:
  • - Inherit from AI Agent — use the voice settings defined in the AI Agent creation settings.
  • - Use Job Voice – apply custom voice settings specific to this job, allowing the AI Agent to adapt to the particular role it performs.
For example, if you create a marketing AI Agent, the voice can be more engaging, friendly, and persuasive. However, if the same AI Agent performs a different role, such as customer support, the voice might be more neutral, empathetic, and formal.
TTS VendorDropdownSelect a TTS vendor from the list or add a custom one. Note that the AI Agent Node doesn’t support TTS Labels to distinguish configurations from the same TTS vendor. To use TTS Labels, add a Set Session Config Node before the AI Agent Node in the Flow editor.
Custom (Vendor)CognigyScriptThe Custom parameter appears when you select Custom from the TTS Vendor list. Specify the custom TTS Vendor. For preinstalled providers, use all lowercase letters, for example, microsoft, google, aws. For custom providers, use the name that you specified on the Speech Service page in the Voice Gateway Self-Service Portal.
TTS LanguageDropdownDefine the language of the voice AI Agent output. Ensure this language aligns with the preferred language of the end user.
Custom (Language)CognigyScriptThe Custom parameter appears when you select Custom from the TTS Language list. Specify the language of the AI Agent output. The format depends on the option selected in the TTS vendor; check your TTS vendor documentation. The typical format is as follows: de-DE, fr-FR, en-US.
TTS VoiceDropdownDefine the voice that should be used for the voice AI Agent output. This parameter allows you to customize the AI Agent’s voice by defining its tone, gender, style, and regional specifics, making conversations more personalized and aligned with your brand and target audience.
Custom (Voice)CognigyScriptThe Custom parameter appears when you select Custom from the TTS Voice list. Use this parameter to specify a custom voice, which is often required for region-specific voices. The format depends on the option selected in TTS Vendor and typically follows the pattern language-region-VoiceName. For example, de-DE-ConradNeural for German (Germany) male voice or en-US-JennyNeural for English (US) female voice.
TTS LabelCognigyScriptThe alternative name of the TTS vendor is the one you specify in the Voice Gateway Self-Service Portal. If you have created multiple speech services from the same vendor, use the label to specify which service to use.
Disable TTS Audio CachingToggleDisables TTS audio caching. By default, the setting is deactivated. In this case, previously requested TTS audio results are stored in the AI Agent cache. When a new TTS request is made and the audio text has been previously requested, the AI Agent retrieves the cached result instead of sending another request to the TTS provider. When the setting is activated, the AI Agent caches TTS results but doesn’t use them. In this case, each request is directly sent to your speech provider. Note that disabling caching can increase TTS costs. For detailed information, contact your speech provider.
ParameterTypeDescription
Tool ChoiceSelectorIf supported by your LLM Model, this will determine how tools should be selected by the AI Agent:
  • Auto — tools (or none) are automatically selected by the AI Agent when needed.
  • Required — your AI Agent will always use one of its Tools.
  • None — your AI Agent won’t use a tool.
Use Strict modeToggleWhen the parameter is enabled, strict mode (if supported by the LLM provider) ensures that the arguments passed to a tool call precisely match the expected parameters. Enabling this feature can help prevent errors. However, it may cause a slight delay in the response, especially during the first call after making changes.
ParameterTypeDescription
Process ImagesToggleEnable the AI Agent to read and understand images attachments. Make sure that your LLM provider supports image processing; refer to your provider’s documentation. In addition, make sure that attachments are supported by and activated in your Endpoint, for example, Webchat.
Images in TranscriptSelectorConfigure how images older than the last turn are handled to reduce token usage:
  • Minify — reduces the size of these images to 512x512px.
  • Drop — excludes the images.
  • Keep — sends the max size (this option consumes more tokens).
Limitations and token consumption depend on the LLM used.
ParameterTypeDescription
LLMSelectorSelect a model that supports the AI Agent Node feature. The selected Default model is the model that you specified in Settings > Generative AI Settings of your Project. Select the model that you added earlier while configuring Agentic AI feature. This model will manage your AI Agent.
AI Agent Base VersionSelectorSelect the base version of the AI Agent to use:
  • Fixed Version — select a specific version, such as 1.0, to ensure stability and avoid potential breaking changes. Use this version in production environments or for critical workflows. The version dropdown will be updated as future versions of the AI Agent Node are released.
  • Latest — use the most recent version of the AI Agent Node. While this version ensures access to the latest features, it may cause breaking changes that require manual updates.
When upgrading to a fixed version or switching to the latest, always test your AI Agent carefully to ensure it works with the selected version.
TimeoutNumberDefine the maximum number of milliseconds to wait for a response from the LLM provider.
Maximum Completion TokensSliderDefine the maximum number of tokens that can be used during a process to manage costs. However, if the limit is set too low, the output may be incomplete, as the process could be cut off before it finishes. For example, if you set the maximum tokens to 100, the model will stop generating content once it reaches 100 tokens. This number would be roughly equal to 100 words, depending on the language and tokenization method.
TemperatureSliderDefine the sampling temperature, which ranges between 0 and 1. Higher values, such as 0.8, make the output more random, while lower values, such as 0.2, make it more focused and deterministic.
Include Rich Media ContextToggleControls whether context is added to the prompt. In this case, context refers to text extracted from rich media (Text with Buttons and Quick Replies). This text provides AI Agents with additional information, improving their responses.If the Textual Description parameter in the Say, Question, or Optional Question Node is filled, the context is taken only from this parameter. If the Textual Description parameter is empty, the context is taken from the button titles and alt text in Text with Buttons and Quick Replies. By default, the Include Rich Media Context parameter is active. When this parameter is inactive, no context is added.Examples:
  • If Textual Description is filled:

    Textual Description: Select your preferred delivery option: Standard Delivery or Express Delivery.

    Quick Replies’ buttons: Standard Delivery, Express Delivery.

    Context added to the prompt: Select your preferred delivery option: Standard Delivery or Express Delivery.

  • If Textual Description is empty:

    Textual Description: empty.

    Quick Replies’ buttons: Standard Delivery, Express Delivery.

    Context added to the prompt: Standard Delivery, Express Delivery.

  • If Include Rich Media Context is inactive:

    No context is added to the prompt.

ParameterTypeDescription
Log to System LogsToggleLog errors to the system logs. They can be viewed on the Logs page of your Project. The parameter is inactive by default.
Store in InputToggleStore errors in the Input object.
Select Error Handling ApproachSelectYou can select one of the Error Handling options:
  • Stop Flow Execution — terminate the current Flow execution.
  • Continue Flow Execution — allow the Flow to continue executing, bypassing the error and proceeding to the next steps.
  • Go to Node — redirect the workflow to a specific Node in the Flow, which can be useful for error recovery or customized error handling.
Select FlowSelectThe parameter appears when Go to Node is selected. Select a Flow from the available options.
Select NodeSelectThe parameter appears when Go to Node is selected. Select a Node from the available options.
Error Message (optional)CognigyScriptAdd the optional message to the output if the AI Agent Node fails.
ParameterTypeDescription
Log Job ExecutionToggleSend a debug message with the current AI Agent Job configuration. The message appears in the Interaction Panel when debug mode is enabled. The parameter is active by default.
Log Knowledge ResultsToggleSend a debug message containing the result from a knowledge search. The message appears in the Interaction Panel when debug mode is enabled. The parameter is inactive by default.
Show Token CountToggleSend a debug message containing the input, output, and total token count. The message appears in the Interaction Panel when debug mode is enabled. Cognigy.AI uses the GPT-3 tokenizer algorithm, so actual token usage may vary depending on the model used. The parameter is inactive by default.
Log System PromptToggleSend a debug message containing the system prompt. The message appears in the Interaction Panel when debug mode is enabled. The parameter is inactive by default.
Log LLM LatencyToggleSend a debug message containing key latency metrics for the request to the model, including the time taken for the first output and the total time to complete the request. The message appears in the Interaction Panel when debug mode is enabled. The parameter is inactive by default.
Log Tool DefinitionsToggleSend a debug message containing information about the configured AI Agent tools. The message appears in the Interaction Panel when debug mode is enabled. The parameter is inactive by default.
To test and refine the job settings, use the Interaction Panel on the right side of the screen.To view the AI Agent’s Flow in detail, click Advanced Editor in the upper-right corner.One AI Agent can have multiple jobs. To add another job, click Add Job in the bottom-left corner. Note that each job corresponds to one Flow.

​
Other Operations

  • GUI
  • API
  • CLI
You can view and delete AI Agents, and copy their Reference ID in Build > AI Agents.

​
More Information