Skeptical Summarizer Pattern

Content

{
  "problem": "Summarization agents accept source material at face value, producing summaries that amplify false, misleading, or unsupported claims embedded in the source.",
  "examples": [
    "Summarizing marketing copy or press releases",
    "Condensing op-eds or opinion pieces",
    "Extracting key claims from vendor documentation"
  ],
  "solution": "Before summarizing, apply a structured credibility pre-pass: identify claims in the source, classify each as well-supported, unsupported-assertion, or contradicts-known-facts, then summarize with credibility labels preserved.",
  "anti_patterns": [
    "Applying skeptical mode to verified internal documents — wastes compute and adds noise",
    "Flagging all unverifiable claims as SUSPECT — unverifiability is not falsehood",
    "Omitting ASSERTED claims from summary — they still represent what the source claims"
  ],
  "implementation_steps": [
    "Extract all primary factual claims from source material as a list",
    "For each claim: classify as SUPPORTED (has cited evidence in source), ASSERTED (stated without evidence), or SUSPECT (contradicts external knowledge)",
    "Annotate the summary with credibility indicators: [SUPPORTED], [ASSERTED], [SUSPECT]",
    "For SUSPECT claims: include brief explanation of why they are flagged",
    "Final summary: lead with high-confidence supported claims, separate section for asserted/suspect claims"
  ]
}