With agent AI, companies conduct business more dynamically. Instead of traditional pre-programmed robots and static rules, agents can now “think” and invent alternative paths when invisible conditions arise. For example, using a business domain ontology such as FIBO (Financial Industry Business Ontology) can help keep agents within barriers and avoid unwanted behavior.
The bottleneck is now at the user experience (UX) layer. While the agents are dynamic and transform with ontology-guided data drift, the user interface remains largely static. These experiences with fixed fields and settings can hinder the creative freedom given to agents. Modern standards such as AG-UI (Agent User Interface) It helps streamline communication between UX and agents, but screens still need to be predefined at design time.
Newer technology is taking this to the next level, allowing agents to dynamically render the desired user screen based on specific content. one is A2UI: Agent to User Interface. With A2UI, we first define a UX schema for how components should be represented. This loosely coupled scheme allows agents to create screens based on data.
Agents now communicate with an A2Ui-compatible “renderer” that dynamically renders screens based on JSON content that agents dynamically produce. The screens are completely interactive and can communicate with the respective agents using AG-UI. Companies like copilot kit They are actively building A2UI renderers that can dynamically build the UI from the JSON specification and connect it to the agent via AG-Ui.
Additionally, the use of newer compression standards such as Token Object Notation (TOON) can help achieve highly efficient compression and include schemas like ontology and A2UI in context prompts. Of course, as models become smarter, they will also include the ability to automatically generate A2UI and AG-UI compatible displays through pre-training.
The following diagram explains a view of this architecture.
As shown, the A2UI specification is complementary to an enterprise ontology and focuses on the logical representation of user interface components. Taking an example of loan approval, the ontology will define business concepts such as loans, parties, interest terms, covenants or conditions. This data typically resides in multiple source systems in different forms and a common enterprise ontology helps unify it into a common “language.”" The A2UI specification will define how the components of the user experience will be represented.
In the future, only specifications will need to be changed, rather than individual screens, because screens are generated with new content each time. Additionally, since A2UI uses AG-UI internally, the screens maintain the connection to the original agent that generated the content. Therefore, events such as button clicks and form submissions can be tracked and responded to. This entire experience occurs within a single pane of glass; for example, a traditional chatbot.
The end product of the business is to unite ontology, agents, A2UI JSON, dynamic content screens and AG-UI message exchanges. Everything is driven by the business logic and relationships defined in the ontology, which means there is less left for interpretation by the UX designer and UI developer. We still need these roles in projects, but reusable components are defined and built only once. Rinse and repeat!
For example, you could define that any communication message sent to a user (error, information, warning) is displayed within a panel with your company logo and complies with the ISO 9241-110 standard. With AI agent and A2UI, a dedicated agent can validate these messages and build them on the screen according to standards.
The chat interface is still your primary interface for users, but A2UI components are rendered the same way. More importantly, existing user screens can be reused as templates to dynamically generate newer screens. This makes your company very robust to commercial and regulatory changes.
Patterns like A2UI reduce dependence on the user interface and complement the dynamic nature of business. Imagine that a company suffers an acquisition and must add new logos to thousands of forms. This logic can now be configured in the A2UI specification and the ontology and UI changes will be propagated when users access the forms. This helps companies to be dynamic and improve employee productivity.
Dattaraj Rao is an Innovation and R&D Architect at Persistent Systems.
