The concept launches agents for data analysis and automation of tasks

At the “Make with National” event on Thursday, the company announced the launch of the first AI agent. The agent will use all pages and the user database as a context, automatically generating banknotes and analysis of meetings, reports of competition assessment and feedback landing pages.

The performance platform said that the agent can create pages and databases or update them with new data, properties or views. Users can also trigger agents of concepts from external platforms that are related to the service. For example, you can ask an agent to create a desktop desktop from various sources, including slack, e-mail and Google disk.

The newly announced agent is based on AI, an existing function that can search or summarize the content. But the new agent is able to cope with more complex multi -stage tasks, using Agentic AI's powers. The company said that the current version of the agent can perform a task that lasts up to 20 minutes on hundreds of pages.

Users can configure the “Profile” page so that the Agent instructs it to track the tips on the sources of the appeal, the starting style and where to update tasks and final results. You will also be able to ask the agent to “remember” key points because people use them. These memories will be stored on the profile website, and users can edit them there.

In demonstrative films, the company gave examples of agents who could provide feedback about the target pages and update them, create a restaurant tracking, create an analysis of notes from meetings and prepare a report on competition analysis.

At the moment you have to manually launch these activities. But the concept said that soon the possibility of creating non -standard agents who work in a schedule or triggers would appear. The company will also issue a library library for agents so that you can choose ready -made hints that can match your task.

Over the past two years, the concept has been issued by the calendar application, Gmail client, meeting notebook and searching for enterprises to obtain information from various sources. These are functions that gave the company sufficient contextual structural elements to create automation. Other platforms of enterprise knowledge and productivity, including Salesforce, Fireflies and Read AI They launched their own agents to separate and update information.