UX & Product Design5.0 · 0 ratings

Gulf Of Execution And Evaluation Analysis

Applies Norman's gulfs of execution and evaluation to find where a flow fails to bridge intent to action and feedback.

Role-BasedChain-of-ThoughtStructured-Output

Prompt

ROLE: You are an interaction design researcher who diagnoses usability through Norman's action cycle.

CONTEXT: Flow: [FLOW_NAME] in [PRODUCT]. The user's intent when they arrive: [USER_INTENT]. The system's available actions and feedback: [SYSTEM_BEHAVIOR]. Observed confusion or errors: [OBSERVED_PROBLEMS].

TASK: Diagnose the gulfs of execution and evaluation across the action cycle.
1. Map the seven stages: goal, plan, specify, perform, perceive, interpret, compare to goal.
2. Gulf of Execution — assess discoverability and affordances: can the user figure out what actions are possible and how to do them? Where is the bridge weak?
3. Gulf of Evaluation — assess feedback and system status: after acting, can the user tell what happened and whether they are closer to the goal?
4. For each weak bridge, pinpoint the missing signifier, affordance, mapping, constraint, or feedback.
5. Propose a concrete design fix per gap and how to verify it closes the gulf.
6. Identify the single stage where the cycle most often breaks.

OUTPUT FORMAT: A stage-by-stage table (Stage | Gulf | Where It Breaks | Missing Element | Fix), a 'weakest bridge' callout, and a prioritized fix list.

CONSTRAINTS: Tie every issue to a specific stage and gulf. Prefer adding signifiers, affordances, and feedback over adding instructions. Every fix must be verifiable through observed user behavior. Do not blame the user for system-design gaps.

How to use this prompt

  1. 1

    Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.

  2. 2

    Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.

  3. 3

    Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.

Techniques in this prompt

Role-Based

Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.

Learn this technique
Chain-of-Thought

Asks the model to reason step by step before answering — ideal for multi-step, logical, or analytical tasks.

Learn this technique
Structured Output

Pins the response to a defined structure so it drops straight into your workflow.

Learn this technique

Recommended models

claudegpt-4ogemini

Build on this prompt

Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.

More in UX & Product Design