An Agentic Process represents a sequence of tasks that must be executed to achieve a specific result. These tasks may involve interactions with users, Agents, and Tools.
This is a step-by-step guide to create, test, and publish an Agentic Process that connects two Agents: the first one applies the Globant writing style to a user-provided text and converts it into Markdown format; the second one takes that Markdown content and translates it into the target language selected by the user.
First, log in to the Console. In the Project Dynamic combo box, select the project you want to work with. In this case, Default(DocumTeam) is used.
Next, on the left side of the screen, you will find the Backoffice menu. In this menu, click on The Lab.
A new window opens in the browser with The Lab.
Once inside The Lab, locate the Side Navigation Menu on the left edge of the screen. If the menu is collapsed, click on the arrow icon to expand it.
In this menu, select the Agentic Processes option to access the Agentic Processes Dashboard.
If no Agentic Processes have been created yet, a message saying "No Agentic Processes Configured" will appear. Below that message, click on the New Process button to start creating a new process.
After clicking on the New Process button, a pop-up window titled Process Details will appear on the screen. Here you must complete the following fields:
- Process Name: Enter a unique and descriptive name for the Agentic Process.
- Process Description: Optionally, provide a brief explanation of the purpose of the Agentic Process.
Once the information is complete, click on Save to continue.
After saving, a new tab opens in the Agentic Processes Dashboard, displaying the Process Name defined in the previous step. There, you'll find a grid where you can design your Agentic Process. By default, a Start node appears at the center of the screen. This node represents how the interaction begins.
Click on Start to open the Properties panel on the right side of the screen.
In the Signal name field, define a label for the trigger. In the Type dropdown, you must select one of the following options:
- User: The process starts based on a user-initiated action.
- Artifact: The process is triggered when a specific artifact is created.
If you select Artifact, an additional Inputs section appears, where you must define an artifact type that should trigger the process.
An artifact consists of one or more files that circulate within the process. It can be:
- An input uploaded by the user, either at the beginning or during execution;
- An intermediate or final result generated by a task.
For example, it may consist of a generated document, a response produced by an Agent, or any other type of structured content that represents a deliverable within the process.
An artifact type defines what kind of content can be produced or used within the process. It does not refer to a specific file, but rather to a recognizable category (such as Requirements Document, User Stories, or Technical Specification) which indicates the format, purpose, or expected structure of the artifact.
During execution, the specific artifacts used in the process must match the defined artifact type.
Click on Add+ and, from the dropdown menu, select the appropriate artifact. This step ensures that the process starts only when the specified artifact becomes available.
In this case, the Signal name is set to Start, and the Type selected is Artifact. In the Inputs section, Text is added.
This configuration enables the user to upload a file with the content to be processed. For example, a document that needs to be formatted according to Globant's writing style.
To add a Task node, move your cursor over the Start node. Then, four circular anchor points will appear around it (top, right, bottom, left). When you hover near any of these points, a + icon is displayed.
Click on the + icon that appears when you hover over the anchor point of your choice. Then, a context menu appears with the following options: Task, Event, Finish, and Condition (Agentic, Parallel).
Select Task to add a new task node to the process. This task represents the first action to be executed once the process is triggered.
Once the task is added, the node appears and the Properties panel automatically opens on the right side of the screen, allowing you to configure the task details.
In addition to creating new tasks by clicking on the + icon next to a node, you can also add a task by dragging it directly from the Toolbox.
To do this, go to the Toolbox located in the bottom-left corner and click on Task. Then, drag the new task node to the desired position on the canvas. Once placed, connect the task by clicking on the + icon on the node you want to connect it to. A dotted line will appear, indicating the connection. Once confirmed, the task will be integrated into the process.
To delete a node, click on it. Circles will appear around the node to indicate it is selected. Then, press the Delete key on your keyboard to remove it.
A task in an Agentic Process represents a unit of action that is executed within the process sequence.
Each task can have inputs (such as artifacts generated by previous tasks or user data) and outputs (new artifacts or actions that trigger subsequent tasks).
To configure the task, fill in the available fields in the Properties panel:
- Agent
- Task name
- Task description
- Task context
- Task instructions
- Examples
- Input artifacts
- Output artifacts
- Output variables
At the top of the Properties panel, within the Agent block, click on the Select link. This opens a pop-up window that lists all the Agents previously defined in The Lab for the current Project.
In this window, you can use the search field to filter Agents by name or description. When an Agent is selected, its detailed information is displayed on the right side, including:
Once you've confirmed that this is the Agent you want to use, click on the Select button. The Agent is then assigned to the task, and its name will appear in the Properties panel instead of “Select”.
This task uses the Documentation Assistant Agent to apply Globant’s writing rules and convert the text into Markdown format. To achieve this, this Agent must have two Public Tools configured:
The first Tool enables the Agent to access the content of the artifact uploaded by the user, and the second allows it to save the result as a new artifact within the process.
In the Task section, you must configure the following fields. They allow you to define precisely what the task should do and are combined with the Agent's capabilities to execute the corresponding action.
- Task name: Specify a clear name that identifies the task.
In this case, since the goal is to review the article content, an appropriate name could be: ConvertArticleToMarkdown
- Task description: Provide a brief description of what the task does.
For example: Convert a documentation article to Markdown format, applying correct structure, headings, and style conventions.
- Task context: Include relevant information that gives context to the task, such as details of the overall process or considerations that the Agent must take into account.
For example: This task is part of a documentation workflow in which generated articles must be transformed into Markdown to ensure consistency across publications. The Agent should format the content according to standard Markdown rules, maintaining clarity and proper use of headings, lists, and emphasis.
- Task instructions: Specify clear instructions that guide the Agent in the execution of the task. These instructions are part of the prompt that will be sent to the Agent.
For example: Take the provided article and convert it into a well-structured Markdown document. Use appropriate Markdown syntax for headings, bold, italics, bullet points, and code blocks where needed. Make sure the content remains clear, professional, and aligned with documentation standards.
Note that if you click on the expand icon, a larger editing window will open to make typing easier.
Examples allow you to define input/output pairs that help the Agent understand the expected result. This is especially useful in tasks involving content transformation, such as converting text to Markdown.
To add an example, click on the + Add option under the Examples section. Two fields will appear:
- Enter the example input: Provide a sample of the original content.
- Enter the example output: Show how that content should appear after processing.
Although this section is optional, it is recommended to include at least one example when the output must follow a specific structure or formatting style.
In this case, since the task involves converting an article to Markdown, a useful example would be:
-
Example input:
This is the introduction. It explains how the system works and what the key components are. Features include: easy setup, automatic updates, and compatibility with all major platforms.
-
Example output:
# Introduction
This is the introduction. It explains how the system works and what the key components are.
## Features
- Easy setup
- Automatic updates
- Compatibility with all major platforms
Here you can configure the artifacts that the task will take as input.
In this case, you must define an input artifact because the task needs to process previously uploaded content.
Insert Text as the input artifact. This artifact represents the content provided by the user when the Agentic Process is triggered. Since this is the initial material to be processed, it must be configured as the task’s input.
If the task requires multiple inputs, you can add them by clicking + Add Artifact. Use the trash can icon to delete an entry you don't need.
This field is mandatory to ensure that the task generates an output that can be used by subsequent tasks in the Agentic Process.
You can define one or more output artifacts and output variables depending on what the task needs to return. Use + Add Artifact to include additional output artifacts, or + Add Variable to specify extra variables that will be available for the following tasks.
In this case, since the task involves validating a documentation article, an appropriate output would be an artifact of type MarkdownArticle, or similar, containing the corrected and validated content.
Once all the necessary fields are configured, the task node will be displayed as follows:
To continue building the Agentic Process, add a second task node following the same procedure described earlier.
This task uses the Expert Translator Agent to translate the article (already converted to Markdown) into the target language specified by the user. This Agent must have the Tools com.globant.geai.read_process_artifact and com.globant.geai.create_artifact configured.
- Agent: Click on the Select link in the Properties panel and choose the ExpertTranslator Agent from the list.
- Task name: TranslateMarkdownArticle
- Task description: Translate a Markdown article into the target language provided by the user.
- Task context: This task is executed after the article has been reformatted to Markdown. Its purpose is to make the content accessible in the language selected by the user, while maintaining structure and readability.
- Task instructions: Translate the provided Markdown content into the target language {{language}}. Make sure to preserve the original formatting, structure, and headings used in the Markdown document. The output should remain clear, professional, and easy to read.
Note: The
{{language}} syntax refers to a process variable. You must define this variable by clicking on the process name (in this case, Documentation Assistant) at the top of the screen, selecting
Edit process variables, and adding a new variable named
language of String type.
- Input artifacts: Select MarkdownArticle, which is the output of the previous task.
- Output artifacts: Define an artifact named TranslatedMarkdownArticle.
Once you have configured the tasks, you can continue building the Agentic Process by adding a new task or event.
To add a new task, follow the same procedure explained in the previous step: go to one of the connection points of the current node (for example, the one at the bottom), click on the + icon and select Task.
If you want to add an event instead, click on the same + icon and select the Event option from the context menu. This action will insert an event-type node that can be used to handle intermediate situations within the process.
After selecting Event, a new node is inserted and automatically connected to the task. The Properties panel on the right opens automatically, allowing you to define the event that will trigger the next action.
In this panel, complete the following fields:
- Signal name: Enter a descriptive name for the event signal (e.g., MarkdownReady).
- Type: In this field, a dropdown menu will appear with two options: User and Artifact. In this case, you must select User because the event will be triggered when a specific artifact is generated, acting as a continuation signal within the process.
- Inputs: When you select Artifact, the Inputs section is enabled automatically. Here, you must define which artifact should be available for the event to be triggered. This behavior is similar to how the Start node works when configured with the Artifact type.
The event node acts as an intermediate pause in the process and can be triggered either by the generation of a specific artifact or by a user action. In this case, the Type is set to User, which means the process will wait until the user confirms that they want to proceed with the next step.
To complete the process, add a Finish node after the event by clicking on the + icon and selecting Finish, just as you did for the previous elements.
Once the process is complete, you can test how the Agentic Process behaves from an user perspective.
Click on the Run Test button in the bottom-right corner of the screen. This opens the testing panel, where you can simulate the interaction with the Agentic Process.
In the testing panel:
- In the Process variables section, enter the language you want the final output translated into (e.g., English, Portuguese, etc.).
- Fill in the Subject field with a brief title or description for the test execution.
- Upload a document in the Artifact (Text) field. This document will be used as the input for applying the Globant writing style and converting it to Markdown.
Once all fields are completed, click on Run to execute the process.
After clicking on Run, the Agentic Process begins execution. It processes the input using the first task and pauses when it reaches the event node.
At this point, the process waits for user confirmation to proceed. As shown in the image, a MarkdownReady section appears with a Send button next to it.
The yellow dotted lines indicate the path the process has followed so far, showing the sequence of tasks that have been completed up to this point.
At the top of the Testing panel, you can find the artifacts icon. By clicking it, you can view all artifacts generated so far and download them if needed:
- The first is generated by the TranslateMarkdownArticle task and contains the same Markdown article, but translated into the language entered.
- The second is the one produced by the ConvertArticleToMarkdown task.
- The third corresponds to the uploaded document.
If something is not working as expected at this point, you can check the behavior of the process from the Tests window.
At the top of the panel, click Show progress to see the complete tracking. This option allows you to inspect each task, check its status, and view the information generated during execution.
To make viewing easier, you can also resize the Tests window by dragging its edges, as shown below.
Alternatively, you can download the logs by clicking the download icon next to artifacts icon.
Once you have verified that the process executed correctly, click the Send button to complete it. This action confirms that the Markdown version is ready, triggers the next step in the workflow, and allows the process to reach the Finish node.
Once the entire Agentic Process has been configured and tested, the final step is to publish it. To do this, click on the Publish button located in the bottom-right corner of the screen.