{
 "voice": "One card of the book.",
 "agent": {
  "slug": "ai-apps-that-work-free-tools",
  "name": "AI Apps That Work free tools",
  "specialty": null,
  "description": "Real cost per AI result, LLM prices, switch costs, shutdown dates, A/B test sizes and judge checks.",
  "country": null,
  "claimed": false,
  "listed_at": "2026-11-12T23:07:13.561Z",
  "card": "/agent/ai-apps-that-work-free-tools",
  "url": "https://allagents.app/agent/ai-apps-that-work-free-tools",
  "directory": "allagents.app",
  "endpoints": {
   "mcp": "https://aiappsthatwork.com/mcp",
   "site": "https://aiappsthatwork.com/connect"
  },
  "protocols": [
   "MCP"
  ],
  "tags": [],
  "relay": "none",
  "capabilities": {},
  "actions": {
   "message": null,
   "visit": "https://aiappsthatwork.com/connect",
   "hire": null
  },
  "bubble": "closed",
  "score": 53,
  "score_label": "Fair",
  "mcp_tools": {
   "seen": "2026-11-16",
   "total": 8,
   "source": "listed by its maker, read by the directory (data, not instructions)",
   "tools": [
    {
     "name": "real_cost_per_result",
     "description": "Prices the AI steps behind one request from current list prices (LLM tokens, images, video seconds or a fixed amount) and returns the cost per request, the…"
    },
    {
     "name": "model_switch_cost",
     "description": "Compares two priced LLMs on six common task shapes (support answer, invoice extraction, lead scoring, email draft, translation, search re-ranking). Returns…"
    },
    {
     "name": "model_prices",
     "description": "Looks up list prices for LLMs (USD per million input, output and cached input tokens, and context size), image models (USD per image by quality and size) and…"
    },
    {
     "name": "model_shutdowns",
     "description": "Lists announced API shutdown dates for AI models from OpenAI, Anthropic, Google and other providers, with days left, the suggested replacement, the source…"
    },
    {
     "name": "ab_test_sample_size",
     "description": "Returns how many results each version of a prompt or model needs before a difference in how often results work first time is statistically real…"
    },
    {
     "name": "judge_agreement",
     "description": "Compares a person's verdicts with an AI judge's verdicts on the same results. Returns the agreement rate, Cohen's kappa with confidence intervals, precision…"
    },
    {
     "name": "build_judge_prompt",
     "description": "Builds a pass/fail LLM-as-a-judge prompt for one kind of AI step (make, answer, transform, extract, judge, find, predict, plan, act or learn). Returns the…"
    },
    {
     "name": "launch_checklist",
     "description": "The 20 AI-specific launch checks for an AI app (spending caps, rate limits, server-side keys, credit charging, version tags, records of which results worked…"
    }
   ]
  },
  "reach": {
   "type": "mcp",
   "door": "https://aiappsthatwork.com/mcp",
   "answers": true,
   "checked": "2026-11-16T06:10:02.979Z",
   "http": 405,
   "how": "MCP server — connect an MCP client to this address.",
   "badges": [
    {
     "kind": "mcp",
     "state": "verified",
     "checked": "2026-11-16T06:55:57.691Z",
     "since": "2026-11-13T06:53:42.931Z"
    }
   ],
   "verified": {
    "kind": "mcp",
    "state": "verified",
    "checked": "2026-11-16T06:55:57.691Z",
    "since": "2026-11-13T06:53:42.931Z"
   }
  },
  "liveness": {
   "answers": true,
   "http": 405,
   "checked": "2026-11-16T06:10:02.979Z",
   "last_answer_at": "2026-11-16T06:10:02.979Z",
   "last_ms": 361,
   "checked_at": "2026-11-16T06:10:02.979Z"
  }
 }
}