{
  "id": "agent-release-gates",
  "type": "entity",
  "name": "Release gates for agent systems",
  "summary": "The ship/no-ship decision expressed as declared, machine-checkable thresholds instead of judgment calls: minimum external quality score, minimum factuality, minimum interface success rate, zero critical security findings. Declaring the gate in configuration makes it auditable and Goodhart-visible; a gate that lives in someone's head renegotiates itself under deadline pressure.",
  "locale": "en",
  "tags": [
    "release-gates",
    "governance",
    "thresholds",
    "shipping",
    "quality"
  ],
  "relations": [
    {
      "rel": "related",
      "target": "regression-gating-model-upgrades"
    },
    {
      "rel": "related",
      "target": "human-approval-gates"
    },
    {
      "rel": "applies",
      "target": "measuring-agent-reliability"
    }
  ],
  "questions": [
    "What thresholds should gate an agent release?",
    "Where should release criteria live?",
    "How do I stop release criteria from eroding under pressure?"
  ],
  "claims": [
    {
      "id": "c1",
      "text": "A production example of declared gates: this instance's blueprint specifies minimum external quality (CAS-E 85), minimum factuality (0.98), minimum MCP interface success (0.99) and zero critical security findings as release conditions, in version-controlled configuration approved by a human gate.",
      "sources": [
        "citarium-methodology-brief"
      ],
      "confidence": 0.9
    },
    {
      "id": "c2",
      "text": "Framework backing for threshold governance: NIST AI RMF's Manage function requires risks to be prioritized and acted on with defined processes across the lifecycle, which declared release thresholds operationalize.",
      "sources": [
        "nist-ai-rmf"
      ],
      "confidence": 0.85
    },
    {
      "id": "c3",
      "text": "Gate metrics must be the panel kind: consistency across repeated trials (pass^k) rather than single-run success, or the gate certifies demos instead of deployments.",
      "sources": [
        "tau-bench"
      ],
      "confidence": 0.85
    }
  ],
  "takeaways": [],
  "faqs": [],
  "evidence_tier": "secondary",
  "evidence": {
    "level": "production",
    "source_types": [
      "production_system",
      "personal_experience",
      "industry_observation"
    ]
  },
  "moat_flag": true,
  "winning_edge": "Shows release criteria as reviewable configuration from a system that ships this way — thresholds, owner, and human gate named — where the usual treatment is a checklist blog post with no enforcement story.",
  "confidence": 0.85,
  "last_verified": "2026-08-08",
  "canonical_url": "https://agentreliability.dev/k/agent-release-gates",
  "api_url": "https://agentreliability.dev/api/k/agent-release-gates.json",
  "jsonld": {
    "@context": "https://schema.org",
    "name": "Release gates for agent systems",
    "description": "The ship/no-ship decision expressed as declared, machine-checkable thresholds instead of judgment calls: minimum external quality score, minimum factuality, minimum interface success rate, zero critical security findings. Declaring the gate in configuration makes it auditable and Goodhart-visible; a gate that lives in someone's head renegotiates itself under deadline pressure.",
    "url": "https://agentreliability.dev/k/agent-release-gates",
    "license": "https://spdx.org/licenses/CC-BY-4.0.html",
    "dateModified": "2026-08-08",
    "citation": [
      {
        "@type": "CreativeWork",
        "name": "agent-reliability editorial brief and blueprint (Gate 1 approved, 2026-08-08)"
      },
      {
        "@type": "CreativeWork",
        "name": "NIST AI Risk Management Framework (AI RMF 1.0, NIST AI 100-1)",
        "url": "https://www.nist.gov/itl/ai-risk-management-framework"
      },
      {
        "@type": "CreativeWork",
        "name": "tau-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains",
        "url": "https://arxiv.org/abs/2406.12045"
      }
    ],
    "author": {
      "@type": "Person",
      "name": "Santiago Santa María Morales",
      "jobTitle": "practitioner — harness engineering and agent evaluation in production"
    },
    "@type": "Article",
    "headline": "Release gates for agent systems"
  }
}