Review evidence

Verification trail

No claims match the current filter.

Findings

Editorial stances

Superlative, ranking, or comparative language the diff adds. No verdict — a page's own framing isn't fact-checkable — listed so a reviewer can confirm each is a stance the docs should take.

• content/blog/why-switch-to-pulumi/index.md L277 Pulumi makes it trivial to take local AI development to production in the cloud. positioning · found by llm-atomic, llm-holistic

Investigation log

cross-sibling-reads

not run (not in a templated section)

external-claim-verification

6 of 12 claims verified (4 unverifiable, 0 contradicted, 2 framing-drift) · 4 specialists (numerical, cross-reference, capability, framing); 0 cross-specialist corroborations · routed: 0 inline, 2 Pass 1, 0 Pass 2, 10 Pass 3 (verified 5, contradicted 2, unverifiable 3).

cited-claim-spot-checks

not run (no cited claims)

frontmatter-sweep

ran on body + meta_desc + social.{linkedin, twitter}

temporal-trigger-sweep

not run (no trigger words)

code-execution

not run (no `static/programs/` change)

code-examples-checks

not run (no fenced code blocks in content files)

editorial-balance-pass

ran (single-subject, N/A)

Editorial balance

{
  "files": [
    {
      "file": "content/blog/codegen-learnings/index.md",
      "outliers": [
        {
          "heading": "The anatomy of Pulumi Copilot RAG",
          "lines": 89,
          "ratio": 7.4
        },
        {
          "heading": "Wrapping up",
          "lines": 59,
          "ratio": 4.9
        }
      ],
      "sections": [
        {
          "heading": "Using RAG for code generation",
          "lines": 10
        },
        {
          "heading": "The anatomy of Pulumi Copilot RAG",
          "lines": 89
        },
        {
          "heading": "From kitchen to table: testing what works",
          "lines": 12
        },
        {
          "heading": "Wrapping up",
          "lines": 59
        },
        {
          "heading": "Evaluate quality of code generation",
          "lines": 12
        }
      ],
      "stats": {
        "mean": 36.4,
        "median": 12,
        "std": 32.1
      },
      "threshold_flags": [
        {
          "heading": "The anatomy of Pulumi Copilot RAG",
          "lines": 89,
          "ratio": 7.4,
          "type": "section-depth-3x-median"
        },
        {
          "heading": "Wrapping up",
          "lines": 59,
          "ratio": 4.9,
          "type": "section-depth-3x-median"
        }
      ]
    },
    {
      "file": "content/blog/the-present-and-future-of-ai-and-iac/index.md",
      "outliers": [],
      "sections": [
        {
          "heading": "AI transforming infrastructure as code",
          "lines": 18
        },
        {
          "heading": "Infrastructure as Code transforming AI",
          "lines": 19
        },
        {
          "heading": "Conclusion",
          "lines": 2
        }
      ],
      "stats": {
        "mean": 13,
        "median": 18,
        "std": 7.8
      },
      "threshold_flags": []
    },
    {
      "file": "content/blog/why-switch-to-pulumi/index.md",
      "outliers": [],
      "sections": [
        {
          "heading": "What is Pulumi?",
          "lines": 83
        },
        {
          "heading": "Frequently Asked Questions - Why Pulumi?",
          "lines": 249
        }
      ],
      "stats": {
        "mean": 166,
        "median": 166.0,
        "std": 83.0
      },
      "threshold_flags": []
    }
  ],
  "trigger": null
}

History

1. 2026-10-30T12:15:28Z e11307f

   initial review (pending publication)