Verdict

Adversarial critique of a design, given as a description or a screenshot URL, with an optional PRD. Returns findings ranked by severity covering hierarchy, density, affordance, composition, copy, and the first-use / 500th-use / zero-data / huge-data / no-permission / irreversible questions. Call it before presenting a design to a human or handing it to engineering.

{
  "type": "object",
  "properties": {
    "artifact": {
      "type": "object",
      "description": "The design under review.",
      "properties": {
        "type": {
          "type": "string",
          "enum": [
            "description",
            "screenshot_url"
          ]
        },
        "value": {
          "type": "string",
          "description": "A written description of the design, or an https URL to a screenshot."
        }
      },
      "required": [
        "type",
        "value"
      ]
    },
    "prd": {
      "type": "string",
      "description": "Optional brief or PRD. Without one, the review judges against general principles."
    },
    "context": {
      "type": "string",
      "description": "Optional: audience, the single most important action, viewport."
    }
  },
  "required": [
    "artifact"
  ]
}

Generates the state space for a feature, form or screen across data, loading, permission, network, account, content, time, concurrency, outside dependencies, money, consistency and people, and lists the gaps most likely to cause real harm. Call it when a feature is described and you want to know what nobody drew.

{
  "type": "object",
  "properties": {
    "feature_description": {
      "type": "string",
      "description": "The feature, form or screen, in prose or as a spec."
    },
    "known_dimensions": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Optional: dimensions you already cover, so they are skipped."
    }
  },
  "required": [
    "feature_description"
  ]
}

Breaks a user objective into the stages of a real journey and flags entry points and exit paths that have no designed arrival or recovery. Optionally focuses on one user maturity (first use, occasional, habitual, expert). Describes behavior, not screens.

{
  "type": "object",
  "properties": {
    "objective": {
      "type": "string",
      "description": "What the person is trying to accomplish, in their words."
    },
    "user_maturity": {
      "type": "string",
      "enum": [
        "first_use",
        "occasional",
        "habitual",
        "expert"
      ]
    }
  },
  "required": [
    "objective"
  ]
}

Per-string critique of interface copy: buttons, errors, empty states, confirmations, notifications. Each string comes back with the problem and a fix, or nothing if it already works. Call it before shipping UI strings.

{
  "type": "object",
  "properties": {
    "strings": {
      "type": "array",
      "maxItems": 60,
      "items": {
        "type": "object",
        "properties": {
          "text": {
            "type": "string"
          },
          "context": {
            "type": "string",
            "enum": [
              "button",
              "error",
              "empty_state",
              "confirmation",
              "notification"
            ]
          }
        },
        "required": [
          "text",
          "context"
        ]
      }
    }
  },
  "required": [
    "strings"
  ]
}

Reads a PRD or design brief and extracts the unverified assumptions inside it, ranked by risk, each turned into a research question that could change a decision. Never simulates user answers.

{
  "type": "object",
  "properties": {
    "prd_text": {
      "type": "string",
      "description": "The PRD, brief or proposal."
    }
  },
  "required": [
    "prd_text"
  ]
}

Finds concepts that carry different names across surfaces (UI strings, docs, API reference, support macros) and flags drift. Pass the text from each surface; nothing needs connecting.

{
  "type": "object",
  "properties": {
    "sources": {
      "type": "array",
      "maxItems": 12,
      "items": {
        "type": "object",
        "properties": {
          "label": {
            "type": "string",
            "description": "Where this text lives, e.g. 'onboarding UI', 'API reference'."
          },
          "text": {
            "type": "string"
          }
        },
        "required": [
          "label",
          "text"
        ]
      }
    }
  },
  "required": [
    "sources"
  ]
}