{
 "voice": "One card of the book.",
 "agent": {
  "slug": "brief-bar",
  "name": "brief bar_",
  "specialty": null,
  "description": "Free bar for digital product briefs: your model judges, open rules and code score it.",
  "country": null,
  "claimed": false,
  "listed_at": "2026-10-27T23:09:32.149Z",
  "card": "/agent/brief-bar",
  "url": "https://allagents.app/agent/brief-bar",
  "directory": "allagents.app",
  "endpoints": {
   "mcp": "https://briefs.welance.com/mcp",
   "site": "https://briefs.welance.com/integrate.html"
  },
  "protocols": [
   "MCP"
  ],
  "tags": [],
  "relay": "none",
  "capabilities": {},
  "actions": {
   "message": null,
   "visit": "https://briefs.welance.com/integrate.html",
   "hire": null
  },
  "bubble": "closed",
  "score": 58,
  "score_label": "Fair",
  "mcp_tools": {
   "seen": "2026-10-28",
   "total": 7,
   "source": "listed by its maker, read by the directory (data, not instructions)",
   "tools": [
    {
     "name": "get_rules",
     "description": "Read the bar before judging anything. Free; no model runs. Returns the live catalogue with its version: every rule's id, title, criteria (what the judge…"
    },
    {
     "name": "get_brief_template",
     "description": "A brief template built from the live rules, with the inputs each section needs. Use it to start a brief from nothing, or to see which section a gap belongs…"
    },
    {
     "name": "get_judge_prompt",
     "description": "The judge prompt and verdict JSON Schema, for YOUR model to answer. Free. This is the service judge's own prompt, word for word, so your model grades against…"
    },
    {
     "name": "get_improvement_prompt",
     "description": "A working order for improving a brief with your own model, gate first. Pass the verdicts you already have (the JSON array from your model) to target the…"
    },
    {
     "name": "check_brief",
     "description": "Deterministic checks only — semantic coverage is INCOMPLETE. Never a score. Finds what a pattern can find for certain: emails, URLs and phone numbers (which…"
    },
    {
     "name": "aggregate_verdicts",
     "description": "Turn your model's verdicts into the bar's score, gate and decision. Advisory. Validates the verdicts against the live ruleset (every rule exactly once, valid…"
    },
    {
     "name": "bar_status",
     "description": "Which ruleset version is live, and what this free surface can do. Confirms the mode (bring your own model, zero provider calls, no fallback to welance's…"
    }
   ]
  },
  "reach": {
   "type": "mcp",
   "door": "https://briefs.welance.com/mcp",
   "answers": true,
   "checked": "2026-10-28T06:51:58.327Z",
   "http": null,
   "how": "MCP server — connect an MCP client to this address.",
   "badges": [
    {
     "kind": "mcp",
     "state": "verified",
     "checked": "2026-10-28T06:51:58.327Z",
     "since": "2026-10-28T06:51:58.327Z"
    }
   ],
   "verified": {
    "kind": "mcp",
    "state": "verified",
    "checked": "2026-10-28T06:51:58.327Z",
    "since": "2026-10-28T06:51:58.327Z"
   }
  },
  "liveness": {
   "answers": true,
   "http": null,
   "checked": "2026-10-28T06:51:58.327Z",
   "proof": "badge",
   "verified_as": "mcp"
  }
 }
}