Verdict

Get a second opinion before it ships.

Verdict reviews the design, the copy and the brief the way a sharp colleague would: it finds what a user would trip over, says how sure it is, and leaves the decision with you. Six tools, one endpoint, built so an agent can call them before it hands work to a person.

Works with Claude, Cursor, VS Code, Codex, ChatGPT, Gemini and Copilot. How to connect.

One per line, as type: string. Types: button, error, empty_state, confirmation, notification.

Runs on the free demo allowance: 2 calls a day, no signup. Your text goes to the review model and is not stored.

Six reviews, each aimed at one way designs fail.

critique_experience

Find the problems in a design before a user or an engineer does, ranked by how badly each one hurts.

Findings marked critical, warning or note, each with the evidence behind it (observed or inferred) and the smallest fix, then a ship-or-not summary.

What it does and a sample for critique_experience

generate_state_matrix

List every state a feature can be in, including the ones nobody drew.

States grouped by dimension (data, permission, billing, outside services and more), plus a list of likely gaps tagged as stated or inferred.

What it does and a sample for generate_state_matrix

map_journey

Map the stages around a goal and name the entries, exits and interruptions the flow forgot.

Ordered stages for the objective, the ways people arrive that the flow ignores, the ways they leave, and how interruptions are handled.

What it does and a sample for map_journey

audit_copy

Review buttons, errors, empty states, confirmations and notifications, and rewrite the ones that fail.

Each string that has a real problem, the reason it fails, and a replacement. Strings that already work come back untouched.

What it does and a sample for audit_copy

find_assumptions

Pull the unchecked beliefs out of a brief and turn each into a question you could answer this week.

Assumptions ranked by risk, each paired with a research question.

What it does and a sample for find_assumptions

check_terminology

Find one concept that goes by several names across your UI, docs and API.

Concept clusters showing which source uses which term, with the drifting ones flagged.

What it does and a sample for check_terminology

Call it from an agent or from curl.

As an MCP server:

{
  "mcpServers": {
    "verdict": {
      "url": "https://verdict.allthepossibles.com/mcp"
    }
  }
}

Or over REST, one route per tool:

curl -X POST https://verdict.allthepossibles.com/api/audit_copy \
  -H "content-type: application/json" \
  -d '{"strings":[{"text":"Submit","context":"button"}]}'

Pricing

Free

All six tools, 2 calls a day per caller, no key. It is a demo budget and can close early on a busy day. Send your own Anthropic key in an x-anthropic-key header and the limit goes away, because the call runs on your account.

Basic, $5 a month

A key, a higher rate limit and a monthly review allowance.

Pro, $19 a month

Five times the allowance of Basic and the highest rate limit, for CI jobs and agent loops that review everything they produce.

Or take the membership: Pro on this and four other products for $15 a month.