# X_EVAL_MISSING

## Means

a prompt has no eval

## Typical cause

a `definePrompt` with no `defineEval` naming it

## Fix

`defineEval({ name, prompt, cases, scorers, tolerance, baseline })` beside the prompt — for a prompt an `agent()` runs, `defineEval({ name, agent, cases, tools, scorers, tolerance, baseline })` — then `ULTIMATE_EVAL_RECORD=1 x test eval`

[MCP and AI](/error-codes#mcp-and-ai)