New Agent in the Loop Component for Human Intervention in Agentic Flows in wolkvox Studio

wolkvox Studio incorporates the new Agent in the Loop component, based on the Human in the Loop (HITL) approach, which allows integrating human agent participation within automated flows built with Agentic Artificial Intelligence.

With this component, a flow can stop at a specific point and send information to a human agent for review and response generation. Once the intervention is completed, the response can be made available to continue with the logic designed in the Routing Point.

This allows building automations where AI and other components execute much of the process autonomously but maintain the ability to involve a person when a situation requires judgment, validation, supervision, or a manual response.

The Agent in the Loop component is located in wolkvox Studio, within the "Cognitive" tab, in the "AI Conversational Components" group.

Important: Agent in the Loop is available only for Routing Points of the Agentic Engine type.

Agent in the Loop does not determine by itself what the human should do nor does it automatically execute actions on external platforms. Its function is to send the human agent the information defined in its configuration and receive their response. What happens before and after depends on the other components and the logic built into the flow.

For this reason, it can be combined with components such as MCP, Intent, Agentic Deep Research, Agentic DB, Sentinel, and other wolkvox Studio resources to design autonomous processes that escalate to the human team only when necessary.

Benefits

• Control and Governance of Agentic Processes: Allows incorporating human intervention points within complex automations, maintaining operational control when a decision requires review, validation, or human judgment.
• Selective Escalation: It is not necessary to send all management tasks to a person. The flow can previously analyze the information and use Agent in the Loop only in those cases that meet certain conditions.
• Traceability of Human Intervention: The response provided by the agent is recorded and can be consulted later, facilitating the tracking of decisions made during the process execution.
• Integration with Multiple Sources and Processes: The content sent to the agent can come from variables and previous components of the flow. In this way, human intervention can be incorporated into processes related to external platforms, databases, AI analysis, or any other integration available in the Routing Point.
• Input for Continuous Improvement: Human responses and corrections can later be used as information to analyze process behavior, adjust rules, or improve the guidelines used by AI components.

What Can Agent in the Loop Be Used For?

The component is especially useful when a process can operate autonomously in most cases, but there are situations that require human participation.

Some examples include:

• Reviewing an AI-generated response before sending it to a customer.
• Escalating sensitive or exceptional requests.
• Validating content before publishing it on an external platform.
• Requesting human authorization before executing a critical action.
• Reviewing cases where an autonomous agent does not have enough information or confidence.
• Allowing a specialist to draft a response for a specific management task.
• Incorporating human supervision in social media, customer service, sales, support, or back-office processes.
• Combining automatic processes with human decisions within the same Routing Point.

Example: YouTube Comment Management

In the shown scenario, a flow is built in Agentic Engine that monitors comments made on YouTube.

Through integration with the MCP component, the flow obtains new comments published on the channel. Subsequently, different components analyze their content and determine what treatment each one should receive.

For example, a user might write: "I really enjoyed learning about the company's culture. Where can I get more information about opportunities to join the team?"

This example uses YouTube, but Agent in the Loop is not limited to this platform. The same principle can be applied to other tools integrated via MCP or information obtained through other wolkvox Studio components.

When the flow reaches Agent in the Loop, an interaction is generated for the configured skill or agent.

In wolkvox Agent, the user must go to the Interactions section located in the left side menu.

The new interaction will appear in the inbox with the subject previously defined in the component. When selected, the agent can review all the information sent from the flow in the right panel.

In this current example, the flow can evaluate the comment and determine whether it can be responded to automatically or if it requires human attention.

When human intervention is required, the route reaches the Agent in the Loop component. This generates an interaction for the agent in charge, including the information configured in the Subject and Body fields.

The agent then receives an interaction with data such as:

• Person who made the comment.
• Comment content.
• Date.
• Video identifier or reference.
• Management status or context.

The content will depend entirely on the variables and data incorporated into the flow.

In the YouTube example, an interaction titled Video Comment Alert is shown, and within it, the comment content and other information collected by the process appear.

To intervene:

1. Open the interaction.
2. Review the information sent by the flow.
3. Click on "Reply."
4. Write the response in the text field.
5. Click on "Send."

The response will be associated with the interaction and can continue within the logic defined in the process.

How to Configure Agent in the Loop

1. Double-click on the component to open its configuration panel.
2. Configure its fields:
   • Subject: Define the title that will allow the agent to quickly identify the purpose of the interaction.
     • For example: Video Comment Alert
   • Body: Define all the information you want to deliver to the agent so they can make a decision or generate a response. This field can include variables from the Routing Point, so it is possible to send information previously obtained through AI components, MCP, data queries, or other stages of the flow.
     • For example, the body could contain:
       • Person's name: $nombre_usuario
       • Comment: $comentario
       • Date: $fecha
       • Video: $video_id
       • Management status: Human attention
   • Transfer to a Skill: Select the skill or agent queue responsible for handling this type of request. All agents enabled for that skill can receive the interaction according to the defined operational rules.
   • Prioritize an Agent ID: If you want to direct the interaction primarily to a specific person, enter their agent ID. This is useful when certain decisions need to be reviewed by a specific agent or specialist.
   • Simultaneous Interactions per Agent: Define how many interactions of this type an agent can manage simultaneously. This value allows controlling the workload generated by autonomous processes.
   • The Result Variable (informative only) field displays the predefined variable: $agent_in_the_loop_response
     • This variable cannot be modified.
     • It stores the response sent by the human agent, allowing other components of the Routing Point to use it later.
     • The response accepted by this mechanism is text. Attachments are not considered as a result of the component.
     • For example, an MCP component located later in the flow could receive: $agent_in_the_loop_response
     • and use that information as part of its instructions.
   • After completing the configuration, click on "Save Agent in the Loop."
   • Subsequently, compile the Routing Point.

---

New Smart Survey Time

The global parameter for the minimum call duration required to transfer to the Smart Survey module has been updated. Previously, this value was set by default to 45 seconds, which caused any call with a duration shorter than this threshold not to be redirected to the satisfaction survey. With this modification, the minimum interaction limit has been reduced to 20 seconds. This improvement resolves the loss of feedback on short but effective calls (such as quick queries, data confirmations, or cancellations), expanding the universe of users who can be surveyed.

Benefits

• Greater Measurement Coverage: Significantly increases the survey capture rate by including brief interactions that were previously excluded from the flow.
• More Accurate Metrics: Allows evaluating customer satisfaction in quick transactions and first-call resolution (FCR), obtaining a more comprehensive view of the service.
• Reduction of Bias in Reports: Avoids excluding efficient short-duration calls that represent a significant volume of daily operations.
• Optimization of Customer Experience (CX): Ensures that users who resolve their request in a few seconds also have the opportunity to evaluate the service received.

---

Improvement in Preview Campaigns

This new feature in Preview Campaigns allows agents to mark records that are in the FREE state using the search tool, even when they have one or more assigned records pending management. Previously, the platform blocked the marking of new records if the agent already had previous assignments in the queue. With this update, that restriction is removed, granting operational freedom for the agent to search for and initiate calls on available contacts immediately when the business strategy or urgency of management requires it.

Benefits

• Operational Flexibility: Grants autonomy to the agent to select and contact key or priority records without being limited by their previous assignment queue.
• Agility in Management: Reduces downtime and eliminates administrative blocks, allowing immediate attention to clients who require it.
• Workflow Optimization: Adapts manual dialing in Preview campaigns to dynamic day-to-day situations (such as follow-up incoming calls or direct requests from supervision).
• Improved Contactability: Increases the probability of contact by allowing real-time search and management of free records within the database.

---

WhatsApp to Email Component

The new Transfer WhatsApp to Email component is an omnichannel integration module designed for wolkvox Studio. Its main purpose is to act as a bidirectional bridge that converts an incoming WhatsApp message into an email directed to an assigned advisor (based on the selected skill), and subsequently captures the response that the advisor sends from their traditional email client (e.g., Gmail, Microsoft 365, corporate or personal email) to automatically return it to the end customer via WhatsApp. This flow resolves the need to handle instant messaging interactions from email environments without losing the thread of the conversation or traceability in the database.

Benefits

• Operational Flexibility for Advisors: Allows agents to handle and respond to WhatsApp queries directly from their usual email inboxes, without the need to keep the web management platform open.
• Traceability and Continuous Context: Uses a unique identifying email address to relate each advisor's response to the session and the customer's phone number on WhatsApp, ensuring a centralized historical record.
• Automated Omnichannel: Eliminates friction between synchronous communication (WhatsApp) and asynchronous communication (Email) through dynamic processing of message inputs and outputs.
• Agile Integration in wolkvox Studio: Facilitates administrators to incorporate contingency flows or deferred attention through a single component in the visual scripting interface.

---

New Integration with Microsoft Teams

The integration of the Microsoft Teams channel allows wolkvox clients to interact directly with their customers through the Teams application. The connection uses Microsoft's Bot Framework to receive and send messages, as well as to manage attachments, enabling smooth and bidirectional communication.

Integration Components

Prerequisites

Azure

• Active Microsoft Azure subscription.
• Contributor or Owner permissions in the subscription.
• Access to Azure Active Directory with application administrator permissions.
• Application registration enabled in Azure AD.

wolkvox

• Access to the wolkvox platform with valid credentials.
• A routing point or routing point available for the bot.

Technical Requirements

• Updated web browser: Chrome, Firefox, or Edge.
• Teams Desktop or Teams Web to install the application.
• Internet access to connect with Azure.