An Agentic Process represents a sequence of tasks that must be completed to achieve a specific result. These tasks can include interactions with users, Agents, and Tools.
This step-by-step guide explains how to create, test, and publish an Agentic Process that connects two Agents. The first Agent applies the Globant writing style to user-provided text and converts it to Markdown format. The second Agent takes the Markdown content and translates it into the target language selected by the user.
First, log in to Glob.AI OS. In the Navigation header, select the Organization and Project you want to work with. In this case, Demo is used as the Organization and Documentation as the Project. Then, from the Hub selector, select Agentic Hub.
Next, locate the side menu on the left side of the screen. In this menu, click Build > Agentic Process.
The Agentic Process Dashboard opens in the central working area of the Agentic Hub. Click New Process to start creating a new Agentic Process.
If no Agentic Processes have been created yet, the message "No Agentic Processes Configured" is displayed.
After you click the New Process button, the Process Details dialog box appears. Complete the following fields:
- Process Name: Enter a unique and descriptive name for the Agentic Process. For example, Documentation Agentic Process.
- Process Description: Optionally, enter a brief description of the purpose of the Agentic Process. For example, Transforms user-provided text into structured Markdown format and translates it into a target language.
Once the information is complete, click 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 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 list, select one of the following options:
- User: The process starts as a result of a user-initiated action.
- Artifact: The process is triggered when a specific artifact is created.
If you select Artifact, an additional Input 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 + Add Artifact and enter the Artifact details to create a new 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. Under Artifact Name, add Text to define the input.
This configuration enables the user to upload a file with the content to be processed. For example, a document that must be formatted according to Globant's writing style.
To add a Task node, move the cursor over the Start node. Four circular anchor points will appear around it (top, right, bottom, left). When you hover over one of these points, a + icon is displayed.
Click the + icon that appears when you hover over the anchor point of your choice. A context menu appears with the following options: Task, Event, Finish, and Condition (Agentic, Parallel, Exclusive).
Select Task to add a new task node to the process. This task represents the first action to be executed after the process is triggered.
After 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 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 lower-left corner and click Task.
Then, drag the new task node to the desired position on the canvas. After placing it, connect the task by clicking the + icon on the node you want to connect it to. A dotted line will appear to indicate the connection. Once confirmed, the task will be integrated into the process.
To delete a node, click it. Circles will appear around the node to indicate that it is selected. Press the Delete key on your keyboard to remove it.
A task in an Agentic Process represents a unit of work 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, in the Agent section, click the Select link. This opens a dialog box that lists all Agents previously defined in Build > Agents 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:
After confirming that the Agent is the one you want to use, click the Select button. The Agent is then assigned to the task, and its name replaces Select in the Properties panel.
This task uses the Technical Documentation Agent to apply Globant’s writing rules and convert the text to Markdown format.
The Agent does not require any additional Tool configuration to read or generate artifacts. When executed within an Agentic Process, access to the input artifact and the creation of the output artifact are handled automatically.
In the Task section, you must configure the following fields. They define the task behavior and are combined with the Agent's capabilities to perform the required action.
- Task name: Enter a descriptive name that identifies the task.
In this case, since the goal is to review the article content, a suitable name is: ConvertArticleToMarkdown.
- Task description: Enter 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: Provide relevant information that helps the Agent understand the context of the task, such as details of the overall process or considerations it 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.
To make editing easier, select the expand icon to open a larger editor.
Examples allow you to define input/output pairs that help the Agent understand the expected result. This is particularly useful for content transformation tasks, such as converting text to Markdown.
To add an example, click the + Add Example 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 is:
-
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. To delete an entry, select the trash can icon.
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 the information the task must return. Select + Add Artifact to include additional output artifacts, or + Add Variable to define extra variables that will be available for subsequent 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 required fields have been configured, the task node is displayed as follows:
To continue building the Agentic Process, add a second task node by following the same procedure described earlier.
This task uses the Translation Expert Agent to translate the article (already converted to Markdown) into the target language specified by the user.
- Agent: Click on the Select link in the Properties panel and choose the Translation Expert 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.
After configuring the tasks, you can continue building the Agentic Process by adding a new task or event.
To add a 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.
To add an event, click 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 you select 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 waits for the user to confirm that they want to continue to 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 a user's perspective.
Click the Run Test button in the lower-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 (for example, English, Portuguese, etc.).
- In the Subject field, enter 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.
After completing all fields, click Run to execute the process.
When you click Run, the Agentic Process starts executing. 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 that the process has followed so far and show the sequence of completed tasks.
At the top of the Testing panel, select the artifacts icon to view all artifacts generated so far and download them if necessary:
- The first one is generated by the TranslateMarkdownArticle task and contains the same Markdown article, but translated into the language entered.
- The second one is generated by the ConvertArticleToMarkdown task.
- The third one corresponds to the uploaded document.
If the process is not behaving as expected, review it in 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, verify its status, and view the information generated during execution.
To make viewing easier, you can resize the Tests window by dragging its edges. You can also download the logs by clicking the download icon next to the artifacts icon.
After verifying that the process executed successfully, 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 Agentic Process has been fully configured and tested, the final step is to publish it. To do this, click the Publish button in the lower-right corner of the screen.