The dominant AI interface will be a universal conversational layer (chat/voice) for any task. This will be supplemented by specialized graphical UIs for power users needing deep functional control, much like an executive sometimes needs to edit a document directly instead of dictating to an assistant.

While CLIs were an important stepping stone for agentic AI, the industry is rapidly moving back to rich Graphical User Interfaces (GUIs). These new UIs are designed for simultaneous collaboration between a human user and an AI agent, offering a more powerful and intuitive experience.

The evolution from terminal-based interfaces (TUIs) like early Claude Code to graphical user interfaces (GUIs) like Codex is critical. To reach a broader audience beyond developers, AI agents must offer clean, simple, and visual interfaces for managing even complex agentic workflows.

Power users are discovering that direct, conversational interaction with AI agents is more efficient than clicking through graphical user interfaces (GUIs). This signals a shift toward an 'app-less' world where tasks are accomplished via chat, potentially making traditional UI/UX design roles redundant for many applications.

AI is not a feature but a complete reimagining of user experience. Product leaders must now design for interactions that originate outside their app and for users that are not human. The next wave of "users" will be other AI agents interacting directly with your system's agents.

While chatbots are an effective entry point, they are limiting for complex creative tasks. The next wave of AI products will feature specialized user interfaces that combine fine-grained, gesture-based controls for professionals with hands-off automation for simpler tasks.

Even after disclosing that an agent is an AI, prioritizing a human-like conversational experience is critical. Users quickly forget they're talking to a machine if the interaction is natural, which reduces friction and makes the automation more effective and accepted.

Despite predictions that conversational bots, voice, or CLI tools will replace graphical user interfaces, Miller argues diverse cognitive styles ensure multi-modal UIs will remain essential. Some users think visually, while others prefer text. In workflows like corporate booking, clicking a single button or checkbox remains faster and less intrusive than conversational prompts, meaning AI agents will complement rather than eradicate traditional interfaces.

With AI, designers are no longer just guessing user intent to build static interfaces. Their new primary role is to facilitate the interaction between a user and the AI model, helping users communicate their intent, understand the model's response, and build a trusted relationship with the system.