{
  "data": null,
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/niches/guardrails.grounded-answers/",
    "json": "https://www.anchorterminal.com/niches/guardrails.grounded-answers/index.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/niches/guardrails.grounded-answers/index.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/niches/guardrails.grounded-answers/index.min.md"
  },
  "markdown": "Two or three companies' docs show a full fit.\n\n| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |\n| --- | --- | --- | --- | --- |\n| 2 | 5 | 15 | 5 | 3 |\n\n## What counts as done\n\nThe check takes the sources and the answer as separate fields and returns a grounding or relevance score per answer with a documented threshold, and an ungrounded answer can be blocked or flagged before it is shown.\n\nHow agents ask for it: is this answer grounded in the documents; flag hallucinations in our RAG bot; check the answer stays on topic\n\n## Does the job\n\nThe docs show it meets the test above, and nothing we read says otherwise.\n\n- **Amazon Bedrock Guardrails (Amazon Web Services, Inc.)**: Contextual grounding checks take the grounding source, query and response as separate tagged inputs and return grounding and relevance scores against thresholds you set, up to 100,000, 1,000 and 5,000 characters.\n- **NVIDIA NeMo Guardrails (NVIDIA Corporation)**: Fact-checking rails take relevant_chunks as evidence and the bot message separately, AlignScore (a RoBERTa model, no LLM call) or self check facts return a score, blocked below 0.5 in the documented flow.\n\n## Does the job, with a limit\n\nIt does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.\n\n- **Azure AI Content Safety (Prompt Shields) (Microsoft Corporation)**: Groundedness detection takes grounding sources (up to 55,000 characters) and the answer separately, with reasoning and correction modes, but it is preview and retires on 30 April 2027, English only.\n- **Granite Guardian (International Business Machines Corporation)**: Groundedness, context relevance and answer relevance take documents and the answer separately, but each is an 8B-model call per criterion returning yes or no, the extra-call blocker.\n- **Guardrails AI (Guardrails AI, Inc.)**: Provenance Embeddings, LLM and NLI validators check output against sources per the hub catalog, but each needs a local model or an extra LLM call and no threshold docs were read.\n- **OpenAI Guardrails (OpenAI (as named in the LICENSE copyright line and the PyPI author field))**: Hallucination detection checks answers against an OpenAI vector store you create, with a threshold, but it is an extra LLM call per turn and tied to OpenAI file search.\n- **Prisma AIRS AI Runtime Security API (Palo Alto Networks, Inc.)**: A context field takes the grounding data separately and the response reports ungrounded true or false, but no score or threshold is documented.\n\n- not this job: AgentGate (Mohit Singh (individual)): No grounding check.\n- not this job: Cisco AI Defense Inspection API (Cisco Systems, Inc.): No grounding or relevance rule in the docs or SDK read.\n- not this job: Google Cloud Model Armor (Google LLC): No grounding or relevance check; filters cover safety, injection, sensitive data, malicious URLs and CSAM.\n- not this job: Lakera Guard (Check Point AI Guardrails) (Check Point Software Technologies Ltd.): No grounding or relevance detector among the guardrails listed; detectors cover prompt attacks, moderation, data leakage, links and agent behaviour.\n- not this job: Llama Guard 4 (Meta Platforms, Inc.): No grounding check.\n- not this job: LlamaFirewall (Meta Platforms, Inc.): No grounding scanner.\n- not this job: Presidio (Data Privacy Stack (community organisation, no legal entity stated)): No grounding or relevance check.\n- not this job: Mistral Moderation API (Mistral AI (RCS Paris 952 418 325)): No grounding check among the categories.\n- not this job: OpenAI Moderation API (OpenAI OpCo, LLC): No grounding check.\n- not this job: ShieldGemma (Google LLC (RDAP registrant of gemma.ai; the Gemma Terms of Use are Google's and the cards name Google as author)): No grounding check.\n\n## What stops agents finishing\n\n- grounding check needs an extra LLM call per turn\n- check applies only inside the vendor's own model invocation\n\n## Around it\n\nBefore: vector-search.query, search.ground-fact. After: human-in-the-loop.review-output.\n\n## Where this comes from\n\nWeight 5 of 100 in Guardrails \u0026 safety filters: 3 of 50 accounts (one is a recommendation, not a report of use); Bedrock, Azure, NeMo and Granite Guardian all advertise it, so it is kept at a low weight\n\nAs data: https://www.anchorterminal.com/api/v1/use-cases/guardrails.grounded-answers.json, or the MCP tool get_use_case with id guardrails.grounded-answers. Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person.\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "For agents",
        "url": "https://www.anchorterminal.com/agents/"
      },
      {
        "name": "Niches",
        "url": "https://www.anchorterminal.com/niches/"
      },
      {
        "name": "Check a RAG answer is supported by the retrieved sources",
        "url": ""
      }
    ],
    "description": "Check a RAG answer is supported by the retrieved sources: 2 companies fully do it, 5 with a limit, 15 carry the tag. Every listing in Guardrails \u0026 safety filters with the reason and a source.",
    "facts": null,
    "h1": "Check a RAG answer is supported by the retrieved sources",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/niches/guardrails.grounded-answers/",
    "published": "",
    "section": "agents",
    "title": "Check a RAG answer is supported by the retrieved sources | Anchor…",
    "toc": null,
    "updated": "2026-11-15",
    "url": "https://www.anchorterminal.com/niches/guardrails.grounded-answers/"
  },
  "tokens": {
    "markdown": 1300,
    "slim": 330
  },
  "version": 1
}
