An AI agent or automation can show a proposed multi-step plan before execution.
Type UI-UX
Sources 6
Trail checked 2026-06-11 emerging Pre-execution preview of an AI agent's proposed multi-step plan, tools, data access, and expected outputs
Test in lab An agent or automation run has started and spans multiple steps, tools, gates, or side effects.
Type UI-UX
Sources 6
Trail checked 2026-06-11 emerging Live execution trace for an AI agent or automation run after work has started
Test in lab An AI agent or automation can create side effects that affect customers, money, access, production systems, legal status, public content, sensitive data, or external recipients.
Type UI-UX
Sources 7
Trail checked 2026-06-13 anti-pattern Anti-pattern for agentic side effects executed before human authorization
Test in lab A generated answer makes source-dependent claims but no source route is visible.
Type UI-UX
Sources 7
Trail checked 2026-06-13 anti-pattern Unsourced AI answer anti-pattern
Test in lab An AI product displays model certainty, extraction confidence, recommendation score, classifier probability, generated-answer confidence, retrieval rank, or risk score with precision the system cannot justify.
Type UI-UX
Sources 5
Trail checked 2026-06-13 anti-pattern Anti-pattern for uncalibrated or over-exact AI confidence displays
Test in lab A user is introduced to an AI feature whose abilities, limits, data scope, uncertainty, or review needs are not obvious from the normal interface.
Type UI-UX
Sources 5
Trail checked 2026-06-12 emerging First-use or new-feature onboarding that teaches AI capabilities, limits, uncertainty, user control, and recovery paths
Test in lab A generated AI output can influence compliance, customer communication, security, legal, finance, operations, code, policy, or other high-trust work.
Type UI-UX
Sources 5
Trail checked 2026-06-12 emerging Inspectable record of generated AI output, prompt context, model, sources, tools, user actions, versions, and downstream use
Test in lab Users need to create or edit automations that run later based on events, conditions, schedules, or record changes.
Type UI-UX
Sources 7
Trail checked 2026-06-12 emerging Rule authoring surface for defining event triggers, conditions, actions, tests, activation, and runtime safeguards
Test in lab The user needs a back-and-forth assistant conversation with follow-up questions and answer refinement.
Type UI-UX
Sources 5
Trail checked 2026-06-11 emerging Multi-turn conversation surface with transcript, composer, assistant responses, and conversation history
Test in lab Users need to verify generated claims, summaries, recommendations, or extracted facts against source material.
Type UI-UX
Sources 8
Trail checked 2026-06-11 emerging Inline claim-to-source evidence display for generated or summarized content
Test in lab Users must judge whether an AI prediction, classification, recommendation, extraction, risk score, or generated answer is reliable enough to use.
Type UI-UX
Sources 5
Trail checked 2026-06-11 emerging Calibrated reliability and uncertainty display for AI or automated predictions before user action
Test in lab Users can identify wrong, unsupported, stale, unsafe, biased, irrelevant, or wrongly sourced AI output after it is generated.
Type UI-UX
Sources 4
Trail checked 2026-06-12 emerging AI output correction feedback flow with selected claim, reason, scope, consent, receipt, and review state
Test in lab Generated content is expected to be revised before it is copied, saved, sent, published, or applied.
Type UI-UX
Sources 7
Trail checked 2026-06-11 emerging Editable generated draft with provenance, review, and apply controls
Test in lab Users need a person because AI, automation, self-service, or scripted support cannot resolve the situation safely or acceptably.
Type UI-UX
Sources 5
Trail checked 2026-06-12 emerging Control and recovery path that transfers an AI, automation, or self-service case to a human channel or queue
Test in lab An AI agent, workflow, deployment, or automation is ready to perform a high-impact step and must pause for human authorization.
Type UI-UX
Sources 6
Trail checked 2026-06-11 emerging Runtime checkpoint that pauses AI or automation until an eligible human authorizes the next step
Test in lab A model version, provider, lifecycle stage, availability, behavior, or replacement plan changes in a way users may need to understand or act on.
Type UI-UX
Sources 5
Trail checked 2026-06-12 emerging Lifecycle notice for AI model version changes, retirement, migration, capability shifts, or replacement behavior
Test in lab Users must write or revise an AI request before generation, analysis, transformation, or automation begins.
Type UI-UX
Sources 4
Trail checked 2026-06-11 emerging Primary editable input surface for composing and submitting an AI request
Test in lab The AI surface supports open-ended requests and users need examples of useful, supported tasks.
Type UI-UX
Sources 4
Trail checked 2026-06-08 emerging AI prompt starter surface
Test in lab A user needs another AI-generated answer for the same request or a visible recovery path after response failure.
Type UI-UX
Sources 7
Trail checked 2026-06-11 emerging AI response regeneration and same-turn retry control with version and context preservation
Test in lab A user's AI request has missing object, audience, timeframe, source, workspace, permission, output-depth, or action-target boundaries.
Type UI-UX
Sources 5
Trail checked 2026-06-12 emerging AI clarification surface that asks for missing task boundaries before answering, planning, retrieving, or using tools
Test in lab Users need answer-wide evidence coverage before trusting generated content.
Type UI-UX
Sources 7
Trail checked 2026-06-11 emerging Whole-answer source coverage and grounding evidence display
Test in lab Generated text or structured content can be read or monitored before completion.
Type UI-UX
Sources 6
Trail checked 2026-06-11 emerging Incremental generated-output surface that renders response chunks before final completion
Test in lab An AI agent or automation calls tools, functions, APIs, retrieval systems, commands, or integrations.
Type UI-UX
Sources 6
Trail checked 2026-06-11 emerging Inspectable disclosure of AI agent tool calls, inputs, outputs, permissions, and side effects
Test in lab