Principles

For designers

Which Blueprint principles matter most for UX and interaction design in agentic products.

Start with visibility

Designers own the visibility contract: what the agent shows, when it shows it, and how much detail is appropriate at each attention level. The four visibility principles resolve the core tradeoff between transparency and cognitive load. A visible agent state is not the same as a noisy agent state.

Trust surfaces are UX decisions

Approval flows, confirmation dialogs, and handoff moments are not engineering problems — they are design problems. The trust cluster defines when explicit user confirmation is required and what form it should take. Designers set the threshold; engineers implement it. Getting this wrong in either direction erodes trust faster than any model error.

Key principles for designers

Focus on: expose-meaningful-operational-state-not-internal-complexity, align-feedback-with-the-users-level-of-attention, make-hand-offs-approvals-and-blockers-explicit, and optimise-for-steering-not-only-initiating. These four principles cover the majority of agentic UX design decisions.

Core principles for designers6

Principle 2visibility

Ensure that background work remains perceptible

When the system is operating asynchronously or outside the user’s immediate focus, it should provide persistent and proportionate signals that work is continuing.

Principle 3visibility

Align feedback with the user’s level of attention

The system should calibrate the depth and frequency of feedback according to whether the user is actively engaged, passively monitoring, or temporarily absent.

Principle 4trust

Apply progressive disclosure to system agency

Provide the minimum information necessary by default, while enabling users to inspect additional detail when confidence, understanding, or intervention is required.

Principle 6visibility

Expose meaningful operational state, not internal complexity

Present the state of the system in language and structures that are relevant to the user, rather than exposing low-level internals that do not support action or understanding.

Principle 7trust

Establish trust through inspectability

Users should be able to examine how a result was produced when confidence, accountability, or decision quality is important.

Principle 8trust

Make hand-offs, approvals, and blockers explicit

When the system cannot proceed, the reason should be immediately visible, along with any action required from the user or another dependency.

Also relevant

Principle 1delegation

Design for delegation rather than direct manipulation

Design experiences around the assignment of work, the expression of intent, the setting of constraints, and the review of results, rather than requiring users to execute each step manually.

Principle 5delegation

Replace implied magic with clear mental models

The product should help users understand what the system can do, what it is currently doing, what it cannot do, and what conditions govern its behaviour.

Principle 9orchestration

Represent delegated work as a system, not merely as a conversation

Where work involves multiple steps, agents, dependencies, or concurrent activities, it should be represented as a structured system rather than solely as a message stream.

Principle 10delegation

Optimise for steering, not only initiating

The system should support users not only in starting tasks, but also in guiding, refining, reprioritising, and correcting work while it is underway.

Also in this section

For engineers Review guide Start here