This is a step-by-step guide to create, test, and publish an Agent.
First, log in to the Globant Enterprise AI Backoffice. In the Project Dynamic combo box, select the project you want to work with; in this case, Default(Docum Team) is used.
Next, on the left side of the screen, you will find the backoffice menu. In this menu, click on The Lab.
By clicking on The Lab in the Globant Enterprise AI Backoffice, a new window opens in the browser with the Globant Enterprise AI Lab (AI Lab), where the Agents associated with the selected Globant Enterprise AI project are created and managed.
Once inside Globant Enterprise AI Lab, the Agents Dashboard opens by default. From there, you can create an Agent in two different ways:
- Manual Creation: This method gives you comprehensive control over every detail of your Agent’s configuration. You can define specific tasks, select appropriate tools, and fine-tune the Agent's behavior, tailoring it exactly to your requirements.
- Assisted Creation: For a more intuitive and streamlined approach, Globant Enterprise AI Lab provides an assisted creation method guided by Iris, the integrated AI assistant. Simply describe what you want your Agent to accomplish, and Iris will help configure the necessary tasks, reasoning models, and thought processes, simplifying the setup and ensuring effective functionality.
To begin the creation process, select your preferred method:
- Click on either the Manual Creation or Assisted Creation option.
- Click on the Continue button located at the bottom right of the screen.
Depending on the creation method chosen in step 2, you must proceed with one of the following:
After selecting Assisted Creation and clicking on Continue, a chat window will appear with Iris, the AI assistant. Iris will guide you through the process.
At this point, you can provide Iris with information about your Agent in the chat, such as:
- Name: Give your agent a descriptive name (e.g., "Customer Support Agent" or "Data Analysis Assistant").
- Role: Describe the primary function of your agent (e.g., "Assist customers with product inquiries" or "Analyze sales data to identify trends").
- Purpose: Explain the overall goal you want your agent to achieve (e.g., "Improve customer satisfaction" or "Provide data-driven insights to the sales team").
Suppose you want to create a marketing research agent. In the chat window, you could type:
"I want to create an agent named 'Marketing Research Assistant.' Its role is to analyze market trends and competitor activities in the technology industry. The purpose is to provide our marketing team with data-driven insights to inform our marketing strategies and campaigns."
Once you've provided Iris with this information, press Enter or click on the arrow button to send your message.
After selecting Manual Creation and clicking on Continue, you'll see a Configuration tab where you can define essential information about your Agent.
- Name: For example, "Marketing Research Assistant".
- Role: Specify it clearly, such as "Analyzes market trends and competitor activities in the technology industry".
- Purpose: Clearly outline your agent's objective, such as "Provide our marketing team with data-driven insights to inform marketing strategies and campaigns".
In this example, the same Agent described in step 3.1 is defined, where Iris is asked to “create a marketing research agent”.
After entering these details, click on the "Create Agent" button located at the bottom right corner of the screen to complete the agent setup.
Note that even when choosing the manual creation method, a chat panel remains available on the left side of the screen. In this panel, you can still interact with Iris to receive suggestions or assistance while configuring your agent. You can describe the agent you want to build, ask questions, or request help completing certain fields, making the manual process more flexible and guided if needed.
Take a moment to review and finalize its configuration based on your chosen creation method:
If you created your agent using Assisted Creation (with Iris), the system will automatically fill in all the details required for your agent based on your conversation with Iris.
Review the following:
- Configuration tab: This tab focuses on defining your agent's identity and behavior. Review the following:
- Name, Role, and Purpose: Verify that these core elements accurately reflect your instructions to Iris.
- Examples: Iris may suggest examples of how to interact with your Agent. Review these to ensure they align with your expectations.
- Background Knowledge, and Guidelines: Iris might also populate these sections with relevant information.
- Avatar Image: Optionally, you can generate an avatar image based on the Agent’s name and description.
- AI & Tools tab: While Iris handles the initial configuration, it's a good practice to review the AI & Tools tab. Here, you can see the selected AI model, reasoning strategy, and enabled tools.
- JSON tab: Automatically reflects all configuration changes you make, providing a structured view of your agent's configuration.
Although Iris takes care of the initial setup, you retain full control over the configuration of your agent. You can make adjustments in two ways:
- Direct editing: Modify settings directly within each tab. Experiment with different models and reasoning strategies or adjust the enabled tools to optimize your Agent's performance.
- Iris Guidance: If you are unsure about a specific setting or need help, Iris is ready to assist you. In the chat panel on the left, describe the changes you want to make or ask specific questions. Iris can guide you through the options, explain the implications of different settings, and even make the adjustments for you within the configuration.
If you have created your agent using Manual Creation, you have full control over its configuration. Be sure to configure the following:
- Generate Avatar Image (Optional): You may generate an avatar image for your Agent.
- Provide Examples (Optional): Add a few examples of how you intend to interact with the Agent. This helps refine its understanding of your requests.
- Background Knowledge, and Guidelines: Provide any relevant context or specific instructions to guide your Agent's behavior. It is mandatory to complete at least one of these two fields, as they allow to tell the Agent what to do and how to respond.
- Configure AI & Tools tab: Navigate to the AI & Tools tab. Select a suitable AI model and reasoning strategy that aligns with your agent's purpose. Consider the complexity of the tasks you want your Agent to perform and choose a model that can handle them effectively.
In the Agents & Tools to use section, ensure the following tools are enabled:
tool_web_scrap_httpx_post
get_search_api_v1_web_searchget_get
These tools are enabled by default in Globant Enterprise AI Lab and are essential for your Agent to access and process information effectively, especially for a marketing research Agent that needs to gather data from the web.
If you created your agent using Assisted Creation (Iris), the system will automatically fill all the details required for your agent. After confirming the configuration, click on the "Run Test" button at the bottom right corner of the screen to test your agent.
If you created your agent using Manual Creation, once you click on the "Create Agent" button, an on-screen confirmation message will appear indicating the successful creation of the agent. You'll also see new buttons appear at the bottom right corner. To begin testing your manually created agent, click on the "Run Test" button.
In both scenarios, clicking on "Run Test" opens a chat window on the right side of your screen. Here, you can interact directly with your Agent, test its capabilities, evaluate responses, and ensure it operates as intended.
Once you have tested your agent and verified that it works correctly, you can proceed with publishing it. To do so, go to the bottom right corner of the screen and click on the Publish button.
Publishing an Agent allows it to appear in the Playground, making it visible and accessible as another Assistant.
Note that if your Agent uses any Tools, they must be published first. Tool drafts can be used during setup and testing, but must be published before being included in a published Agent.
Since April 2025 release.