With agentic AI, businesses are conducting business more dynamically. Instead of traditional pre-programmed bots and static rules, agents can now “think” and invent alternative paths when unseen situations arise. For example, using a business domain ontology such as FIBO (Financial Industry Business Ontology) can help keep agents within security and avoid unwanted behavior.
The bottleneck is now in the user experience (UX) layer. While agents are dynamic and change with the data flow guided by the ontology, the user interface is still very static. These experiences with fixed areas and configurations can hinder the creative freedom given to agents. Modern standards like AG-UI (Agent User Interface) Help streamline UX and communication between agents – but screens should still be pre-defined at design time.
A new technology is taking this to the next level, dynamically allowing agents to present their desired user screen based on specific content. is there anyone A2UI – Agent of User Interface. With A2UI, we first define a UX schema for how components should be presented. This loosely coupled schema allows agents to create screens according to the data.
Agents now communicate with an A2Ui compliant “renderer” that dynamically renders the screen based on the JSON content that the agents dynamically produce. The screens are fully interactive and can communicate back with the relevant agents using the AG-UI. companies like copilotkit Actively building A2UI renderers that can dynamically build a UI from a JSON spec and tie it back to the agent via AG-Ui.
Additionally, using new compression standards such as Token Object Notation (TOON) Can help achieve highly efficient compression and include ontology and schema like A2UI in context signals. Of course, as models become smarter, they will also include the ability to automatically generate screens tailored to A2UI and AG-UI through pre-training.
The plan below explains one view of this architecture.
As shown, the A2UI specification complements a business ontology and focuses on presenting logic for user interface components. Taking an example of loan approval, the ontology will define business concepts such as loan, parties, interest terms, contracts or terms. This data is usually in multiple source systems in different forms and a common business ontology helps integrate it into a common “language”." The A2UI specification will define how user experience components will be presented.
In the future, only the specification needs to be changed rather than the individual screens, as the screens are generated with fresh content each time. Additionally, since A2UI uses AG-UI under the hood, the screen maintains a connection to the original agent generating the content. Therefore, events like button clicks and form submissions can be tracked and responded to. This entire experience happens inside a single pane of glass – for example, a traditional chatbot.
The business delivery ontology is connecting together agents, A2UI JSON, dynamic content screens, and AG-UI message exchanges. Everything is driven by business logic and relationships defined in the ontology, meaning there is less left for interpretation by the UX designer and UI developer. We still need these roles on projects, but reusable components are defined and built only once. rinse and repeat!
For example, you can define that any communication message (error, information, warning) sent to the user should be presented inside a panel with your company logo and conform to ISO 9241-110. With agentic AI and A2UI, a dedicated agent can validate these messages and make them appear on the screen as per standards.
The chat interface still remains your primary interface to users, but A2UI components are presented similarly. More importantly, existing user screens can be reused as templates to generate new screens dynamically. This makes your business highly robust to commercial and regulatory changes.
Patterns like A2UI reduce reliance on user interfaces and complement the dynamic nature of business. Imagine a company is being acquired and needs to add a new logo to thousands of forms. Now, this logic can be configured in the A2UI spec and ontology and UI changes will be propagated when users access the forms. This helps businesses to be dynamic and improve employee productivity.
Dattaraj Rao is Innovation and R&D Architect at Persistent Systems.
<a href