Treating AI Agents as Personas: Introducing the Era of Agent-Computer Interaction
The UX landscape is evolving. While the design community has quickly adopted Large Language Models (LLMs) as tools, we’ve yet to fully grasp their transformative potential. With AI agents now deeply embedded in digital products, they are shifting from tools to active participants in our digital ecosystems. This change demands a new design paradigm—one that views AI agents not just as extensions of human users but as independent personas in their own right.
The Rise of Agent-Computer Interaction
AI agents represent a new class of users capable of navigating interfaces autonomously and completing complex tasks. This marks the dawn of Agent-Computer Interaction (ACI)—a paradigm where user experience design encompasses the needs of both human users and AI agents. Humans still play a critical role in guiding and supervising these systems, but AI agents must now be treated as distinct personas with unique goals, abilities, and requirements.
This shift challenges UX designers to consider how these agents interact with interfaces and perform their tasks, ensuring they are equipped with the information and resources necessary to operate effectively.
Understanding AI Agents
AI agents are intelligent systems designed to reason, plan, and work across platforms with minimal human intervention. As defined during Google I/O, these agents retain context, anticipate needs, and execute multi-step processes. Advances in AI, such as Anthropic’s Claude and its ability to interact with graphical interfaces, have unlocked new levels of agency.
Unlike earlier agents that relied solely on APIs, modern agents can manipulate graphical user interfaces much like human users, enabling seamless interaction with browser-based applications. This capability creates opportunities for new forms of interaction but also demands thoughtful design choices.
Two Interaction Approaches for AI Agents
- API Integration (Tool Use):
AI agents interact programmatically via APIs. This method is faster and avoids rendering overhead but is limited by API quality and scope. - Visual Interface Interaction (Human Tools):
AI agents engage with software through its graphical interface, mirroring human actions. While slower, this approach offers better transparency and control for human supervision.
Design teams must evaluate these methods based on the task’s complexity and transparency requirements, striking the right balance between efficiency and oversight.
Designing Experiences Considering AI Agents Personas
As AI agents transition into active users, UX design must expand to accommodate their specific needs. Much like human personas, AI agents require a deep understanding of their capabilities, limitations, and workflows.
Creating AI Agent Personas
Developing personas for AI agents involves identifying their unique characteristics:
- Capabilities: What tasks can they perform?
- Goals: What outcomes are they designed to achieve?
- Limitations: Where do they need human support?
These personas inform interface designs that optimize agent workflows, ensuring both agents and humans can collaborate effectively.
New UX Research Methodologies
UX teams should embrace innovative research techniques, such as A/B testing interfaces for agent performance and monitoring their interaction patterns. While AI agents lack sentience, they exhibit behaviors—reasoning, planning, and adapting—that require careful study and design consideration.
Shaping the AI Mind
AI agents derive their reasoning capabilities from Large Language Models (LLMs), but their behavior and effectiveness are shaped by UX design. Designers have a unique role in crafting system prompts and developing feedback loops that refine LLM behavior over time.
Key Areas for Designer Involvement:
- Prompt Design: Crafting clear and effective prompts that guide agent actions.
- Performance Metrics: Establishing criteria to evaluate agent effectiveness.
- Feedback Loops: Leveraging user insights to continuously improve agent behavior.
This work positions UX professionals as co-creators of AI intelligence, shaping not just interfaces but the underlying behaviors that drive agent interactions.
Keeping Humans in the Loop
Despite the rise of AI agents, human oversight and control remain essential. UX practitioners must prioritize transparency and trust in agent-driven systems.
Key Considerations:
- Control: Provide users with mechanisms to monitor and guide AI agents, such as permission settings and opt-out options.
- Transparency: Clearly communicate how AI agents operate, use data, and collaborate with other systems.
Using tools like agentic experience maps—blueprints that visualize the interactions between humans, agents, and products—designers can ensure AI systems remain human-centered.
A New Frontier for UX
The emergence of AI agents heralds a shift as significant as the transition from desktop to mobile. Just as mobile devices unlocked new opportunities for interaction, AI agents are poised to redefine digital experiences in ways we can’t yet fully predict.
By embracing Agent-Computer Interaction, UX designers have an unprecedented opportunity to shape the future of human-AI collaboration. Those who develop expertise in designing for these intelligent agents will lead the way in creating systems that are not only powerful but also deeply human-centered.
Expanding its reach beyond CRM, Salesforce.com has launched a new service called AppExchange OEM Edition, aimed at non-CRM service providers. Read more
In Marc Benioff's own words How did salesforce.com grow from a start up in a rented apartment into the world's Read more
Salesforce.com, a prominent figure in cloud computing, has finalized a deal to acquire Jigsaw, a wiki-style business contact database, for Read more
Following swiftly after last week's successful launch of Financial Services Cloud, Salesforce has announced the second installment in its series Read more
