Intent Preview
What is Intent Preview?
The Intent Preview pattern addresses a core anxiety in agentic AI: users need to understand what will happen BEFORE it happens. Unlike traditional AI where the user explicitly types a prompt and evaluates the response, agentic actions may be initiated proactively or involve consequences that are difficult to reverse - sending emails, booking flights, modifying files. This pattern shows a clear, scannable summary of planned actions using plain language (not technical jargon), with each step marked for reversibility and editable by the user. The preview must be sequential for multi-step operations, highlight irreversible actions visually, and never auto-dismiss. This transforms the approval moment from a binary yes/no into a structured review that builds trust and catches misunderstandings before they cause harm.
Problem
When an agent is about to take a multi-step action, users need to understand what will happen before it happens. Without an intent preview, users experience anxiety leading to constant monitoring or blind trust that erodes at the first mistake.
Solution
Before any significant action, present a clear, scannable preview showing planned steps in plain language, with reversibility indicators, edit controls for individual steps, and explicit approve/reject buttons. Never auto-dismiss the preview.
Real-World Examples
Implementation
AI Design Prompt
Guidelines & Considerations
Implementation Guidelines
Use progressive disclosure within the preview itself - show the summary first ('3 actions planned'), let users expand for detail.
Highlight irreversible actions visually with different color or warning icon. Sending an email deserves more visual weight than drafting a document.
Include a time estimate. 'This will take approximately 2 minutes' sets expectations for multi-step operations.
For recurring tasks, offer 'always approve this type' to graduate to higher autonomy over time.
Never auto-dismiss a preview. The user must explicitly approve, even if it's just a single tap.
Make individual steps editable - users should be able to modify, reorder, or remove steps, not just approve or reject the entire plan.
Use plain language descriptions, not technical jargon. Show 'Cancel your flight to San Francisco' not 'Execute cancel_booking(id: 4A7B)'.
Design Considerations
Preview-to-approval rate: how often users approve without modifications indicates preview quality
Preview-to-edit rate: how often users modify the plan indicates the preview caught misunderstandings
Preview skip rate: if users start skipping previews, consider graduating them to higher autonomy
Balancing preview frequency with user fatigue - not every action needs a full preview
Determining the right level of detail for each action type to avoid information overload
Ensuring the preview accurately reflects what will happen to maintain trust
Supporting both quick-scan and deep-review modes for different user contexts
See this pattern in your product
Upload a screenshot and find out which of the 36 patterns your AI interface uses.
Related Patterns
Progressive Disclosure
Gradually reveal information, options, or AI features to reduce cognitive load and simplify complex tasks.
Natural InteractionHuman-in-the-Loop
Balance automation with human oversight for critical decisions, ensuring AI augments human judgment.
Human-AI CollaborationAutonomy Spectrum
Provide a spectrum of autonomy levels - from passive suggestions to full autonomy - that users can adjust per task type, enabling granular control over how independently an AI agent operates.
Human-AI CollaborationPlan Summary
Provide a structured breakdown of the agent's reasoning and approach - showing goal interpretation, strategy, subtask checklist, and assumptions - so users can evaluate the plan before execution begins.
Trustworthy & Reliable AI