Agentic Experience Design



Agentic Experience Design (Link), with free guides, research and tools on how people and AI agents work together on a task — with an agent journey map, human-agent interaction modes, and how to design for trust and oversight. Neatly put together by Alan W.

Agent Journey Map →

Design Patterns For Agentic UX →

—

🔸 1. Meet Agentic Experience (AX)

The key difference between AI and AI agents is autonomy. Agents have agency — they can perform actions on behalf of humans or other agents, with or without approvals and feedback loops, and they can choose the actions to perform depending on their goals.

These goals can be broad or specific — gathering data, filing a support ticket, buying something or contacting a supplier. But they are always shaped towards a particular intent that a user has expressed in some way.

Because that articulation can happen inside or outside our products, we need to set up paths for agents to maximize their success, even with ambiguous or incomplete input. We do so by guiding them. With structured content, instructions on how to choose the right route for key tasks — and how to recover from failures.

—

🔹 2. The Two Sides of Agentic Experiences

When we speak about agentic experiences, typically there is quite a bit of confusion in the room. Are we actually speaking about agents’ experiences towards a goal? Or human experiences of using agents to achieve their goals?

Typically it’s both. We design for “agent accessibility” — to help external agents be more efficient and successful with our products. And we help our users work with our (or their) AI agents — from initial setup and preview to running and correcting. It means showing what agent does, gradual consent and autonomy, and the right level of trust and confidence.

—

🔺 3. In-, On- and Out-Of-The-Loop

Any given task typically crosses 3 human-agent interaction modes (https://lnkd.in/dHgSitVs), with different levels of autonomy or oversight — depending on reversibility and consequences of actions. Most UX work is deciding when and how to switch between them.

⦿ In-the loop
Agent plans and proposes, human approves before anything happens. The work stops at each step and waits for approval. We use it when the action can’t be undone, will be seen by other people or costs money. Beware of  approval fatigue.

⦿ On-the loop
The agent runs without waiting, while a human watches the work as it happens and can step in at any moment. Works for long tasks with many steps, made of small, low-risk actions. Research, comparing and edits across many files all fit.

⦿ Out-of-the loop
Agent works autonomously, (hopefully!) within boundaries agreed, and reports afterwards. Oversight happens when users define what’s allowed beforehand, and when they review afterwards. Works for scheduled tasks, e.g. nightly digests, monitoring and alerts.

↓

    Agentic Experience Design (Free Guide)