Back to Details

narrative-tracker

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

/digital-marketing-pro:narrative-tracker

/digital-marketing-pro:narrative-tracker

Purpose

用途

Track and analyze the narrative that AI engines construct about the brand. Monitor what ChatGPT, Perplexity, Gemini, and others say when asked about the brand, compare to desired positioning, detect drift or misrepresentation, and identify when competitors are gaining narrative territory in AI responses. Unlike visibility monitoring (which measures whether the brand appears), narrative tracking measures what is said — the qualitative story AI engines tell about the brand, whether it aligns with intended positioning, and how it changes over time. This gives marketers the insight to proactively shape AI perception through targeted content strategy rather than reacting after damage is done.
追踪并分析AI引擎构建的品牌叙事。监控ChatGPT、Perplexity、Gemini等AI工具在被问及品牌时的表述，与期望的品牌定位进行对比，检测叙事漂移或信息误传，并识别竞争对手何时在AI回复中抢占叙事领地。与可见性监控（衡量品牌是否出现）不同，叙事监控关注的是具体表述——AI引擎讲述的品牌定性故事、是否与预期定位一致，以及随时间的变化情况。这能让营销人员获得洞察，通过针对性内容策略主动塑造AI对品牌的认知，而非在损害发生后被动应对。

Input Required

所需输入

The user must provide (or will be prompted for):
  • Desired brand positioning statement(s): The core positioning the brand wants AI engines to reflect — value proposition, market position, key differentiators, and target audience. If not provided explicitly, these are extracted from the brand profile's positioning and messaging sections
  • Key brand attributes to verify in AI responses: Specific attributes, claims, or themes that should appear when AI engines describe the brand — e.g., "enterprise-grade security", "founded in 2015", "serving 10,000+ customers", "leader in [category]". These become the checklist for narrative alignment scoring
  • Competitor brands to track narrative for: One or more competitors whose AI narratives should be monitored alongside the brand — enables detection of narrative territory shifts where a competitor begins owning themes previously associated with the user's brand
  • AI platforms to monitor: ChatGPT, Perplexity, Gemini, AI Overviews, Copilot — default is all. The user can narrow to platforms most relevant to their audience or where they have observed issues
  • Query types: Brand queries ("Tell me about [brand]"), comparison queries ("[brand] vs [competitor]"), category queries ("best [category] solutions"), and problem-solution queries ("how to solve [problem brand addresses]"). A balanced mix is recommended for comprehensive narrative coverage
用户必须提供（或会被提示提供）：
  • 期望的品牌定位声明：品牌希望AI引擎反映的核心定位——价值主张、市场地位、关键差异化点和目标受众。如果未明确提供，将从品牌档案的定位和信息传递部分提取
  • 需在AI回复中验证的关键品牌属性：AI引擎描述品牌时应体现的特定属性、主张或主题——例如“企业级安全”“成立于2015年”“服务10000+客户”“[品类]领导者”。这些将作为叙事一致性评分的检查清单
  • 需追踪叙事的竞争品牌：一个或多个需与自身品牌同时监控叙事的竞争对手——便于检测叙事领地转移，即竞争对手开始占据此前与用户品牌相关的主题
  • 需监控的AI平台：ChatGPT、Perplexity、Gemini、AI Overviews、Copilot——默认监控全部平台。用户可缩小范围至与受众最相关或曾出现问题的平台
  • 查询类型：品牌查询（“介绍一下[品牌]”）、对比查询（“[品牌] vs [竞争对手]”）、品类查询（“最佳[品类]解决方案”）、问题解决方案查询（“如何解决[品牌所针对的问题]”）。建议混合使用各类查询以实现全面的叙事覆盖

Process

流程

  1. Load brand context: Read 
    ~/.claude-marketing/brands/_active-brand.json
    for the active slug, then load 
    ~/.claude-marketing/brands/{slug}/profile.json
    . Extract brand positioning, key messages, differentiators, value propositions, target audience, and competitive claims — these form the reference narrative against which AI responses are evaluated. Also check for guidelines at 
    ~/.claude-marketing/brands/{slug}/guidelines/_manifest.json
    — if present, load messaging dos/don'ts and positioning guardrails. If no brand exists, ask: "Set up a brand first (/digital-marketing-pro:brand-setup)?" — or proceed with user-provided positioning statements.
  2. Query AI platforms and record narratives: For each query on each platform, capture the full AI-generated response and extract the narrative — what does the AI say about the brand, how does it position it relative to alternatives, what attributes does it highlight, what does it omit, and what does it get wrong. Record the complete response text, not just scores, because narrative analysis requires the actual language and framing used by the AI engine.
  3. Score narrative alignment: Compare each AI response against the desired positioning on key dimensions. For each key brand attribute, mark as present (AI includes it accurately), absent (AI omits it), distorted (AI includes it but frames it incorrectly or negatively), or outdated (AI references an old version of this attribute). Flag misrepresentations where the AI states something factually incorrect about the brand. Flag narrative drift where the AI's positioning of the brand has shifted from the previous check — even if not incorrect, the framing or emphasis has changed. Calculate a narrative alignment score per platform and per query type.
  4. Track competitor narratives: Run the same query types for each competitor brand. Record what AI engines say about competitors — their positioning, highlighted attributes, and claimed differentiators. Identify narrative territory shifts — themes or attributes that were previously associated with the user's brand but now appear in competitor descriptions, or neutral territory that a competitor has begun to claim. Map which brand "owns" which narrative themes in AI responses.
  5. Record all narratives: Store full narrative data via 
    geo-tracker.py track-narrative
    with timestamp, brand slug, platform, query, full response text, alignment score, attribute presence/absence/distortion flags, misrepresentation flags, and competitor narrative data.
  6. Compare to previous snapshots: If previous narrative data exists, diff current narratives against the most recent previous check. Detect new themes the AI has started associating with the brand, lost themes that no longer appear, shifted framing where the same attribute is described differently, resolved issues where previously flagged misrepresentations have been corrected, and new issues that have appeared since the last check.
  7. Generate narrative correction strategy: Based on all findings, produce a targeted content strategy to influence AI perception — content to create that establishes missing attributes in citable sources, content to update that corrects outdated information AI engines are citing, structured data and entity updates that reinforce correct positioning, citation opportunities on high-authority platforms that AI engines trust, and defensive content for queries where competitors are gaining narrative territory.
  1. 加载品牌上下文：读取
    ~/.claude-marketing/brands/_active-brand.json
    获取活跃品牌标识，然后加载
    ~/.claude-marketing/brands/{slug}/profile.json
    。提取品牌定位、关键信息、差异化点、价值主张、目标受众和竞争主张——这些构成评估AI回复的参考叙事。同时检查
    ~/.claude-marketing/brands/{slug}/guidelines/_manifest.json
    中的准则——如果存在，加载信息传递的注意事项和定位约束。如果没有品牌档案，询问：“是否先设置品牌（/digital-marketing-pro:brand-setup）？”——或使用用户提供的定位声明继续。
  2. 查询AI平台并记录叙事：针对每个平台的每个查询，捕获完整的AI生成回复并提取叙事内容——AI对品牌的表述、如何将其与竞品对比、突出哪些属性、遗漏了什么、存在哪些错误。记录完整回复文本，而非仅记录分数，因为叙事分析需要AI引擎使用的实际语言和框架。
  3. 评分叙事一致性：将每个AI回复与期望定位在关键维度上进行对比。对于每个关键品牌属性，标记为存在（AI准确提及）、缺失（AI未提及）、失真（AI提及但框架错误或负面）或过时（AI引用该属性的旧版本）。标记AI对品牌的事实性错误表述。标记叙事漂移，即与上次检查相比，AI对品牌的定位发生了变化——即使表述无误，但框架或重点已改变。计算每个平台和每种查询类型的叙事一致性得分。
  4. 追踪竞争对手叙事：针对每个竞争品牌运行相同类型的查询。记录AI引擎对竞争对手的表述——他们的定位、突出的属性和宣称的差异化点。识别叙事领地转移——此前与用户品牌相关但现在出现在竞争对手描述中的主题或属性，或竞争对手开始抢占的中立领地。绘制AI回复中各品牌“占据”哪些叙事主题的图谱。
  5. 记录所有叙事：通过
    geo-tracker.py track-narrative
    存储完整叙事数据，包括时间戳、品牌标识、平台、查询、完整回复文本、一致性得分、属性存在/缺失/失真标记、误传标记和竞争对手叙事数据。
  6. 与过往快照对比：如果存在过往叙事数据，将当前叙事与最近一次检查的数据进行对比。检测AI开始与品牌关联的新主题、不再出现的丢失主题、同一属性描述方式变化的框架转移、此前标记的误传已纠正的已解决问题，以及自上次检查以来出现的新问题。
  7. 生成叙事修正策略：基于所有发现，制定针对性内容策略以影响AI认知——创建可在可信来源中确立缺失属性的内容、更新纠正AI引擎引用的过时信息的内容、强化正确定位的结构化数据和实体更新、在AI引擎信任的高权威平台上获取引用机会，以及针对竞争对手抢占叙事领地的查询制作防御性内容。

Output

输出

A comprehensive narrative tracking report containing:
  • Narrative alignment report: Per-platform and per-query-type alignment scores showing how well AI responses match desired brand positioning, with overall narrative health score and trend vs previous check
  • Misrepresentation flags: Specific factual inaccuracies found in AI responses — what the AI said, what is actually true, which platform, which query triggered it, and severity (minor inaccuracy, significant error, or damaging misrepresentation)
  • Narrative drift indicators: Changes in how AI engines frame the brand compared to previous checks — shifted emphasis, new associations, lost associations, and tone changes — even when not factually incorrect, drift signals that AI perception is evolving away from desired positioning
  • Competitor narrative comparison: Side-by-side analysis of how AI engines describe the brand vs each competitor — attribute ownership, positioning differences, and relative narrative strength per platform
  • Narrative territory map: Visual mapping of which brand "owns" which themes and attributes in AI responses — showing shared territory, contested territory, and unoccupied territory that represents opportunity
  • Content recommendations: Specific content to create or update to correct narrative issues, strengthen weak attributes, defend contested territory, and claim unoccupied narrative space — with target platform, format, and expected narrative impact
  • Trend over time: Narrative alignment score history across monitoring periods, with key events annotated (content published, entity updated, competitor launched campaign) to correlate actions with narrative shifts
  • Execution log entry: Timestamped record with platform count, query count, overall alignment score, misrepresentation count, drift flags, and key narrative changes for audit trail
一份全面的叙事追踪报告，包含：
  • 叙事一致性报告：各平台和各查询类型的一致性得分，显示AI回复与期望品牌定位的匹配程度，以及整体叙事健康得分和与上次检查的趋势对比
  • 误传标记：AI回复中发现的具体事实错误——AI的表述、实际情况、涉及平台、触发查询及严重程度（轻微不准确、重大错误或有害误传）
  • 叙事漂移指标：与上次检查相比，AI引擎对品牌框架的变化——重点转移、新关联、丢失关联和语气变化——即使表述无误，漂移也表明AI对品牌的认知正偏离期望定位
  • 竞争对手叙事对比：AI引擎对自身品牌与各竞争对手描述的并列分析——属性占据情况、定位差异以及各平台的相对叙事实力
  • 叙事领地图谱：可视化绘制AI回复中各品牌“占据”哪些主题和属性——显示共享领地、竞争领地以及代表机会的未被占据领地
  • 内容建议：用于纠正叙事问题、强化薄弱属性、防御竞争领地和抢占未被占据叙事空间的具体创建或更新内容——包含目标平台、格式和预期叙事影响
  • 长期趋势：各监控周期的叙事一致性得分历史记录，并标注关键事件（发布内容、更新实体、竞争对手发起活动）以关联行动与叙事变化
  • 执行日志条目：带时间戳的记录，包含平台数量、查询数量、整体一致性得分、误传数量、漂移标记和关键叙事变化，用于审计追踪

Agents Used

使用的Agent

  • seo-specialist — Narrative analysis across AI engine responses, positioning alignment assessment against brand profile, attribute presence and distortion detection, citation strategy for influencing AI perception, content optimization recommendations for narrative correction, structured data and entity update guidance to reinforce accurate brand positioning in knowledge sources
  • competitor-intelligence — Competitive narrative tracking across AI platforms, narrative territory mapping between the brand and competitors, territory shift detection where competitors gain or lose narrative themes, competitive positioning comparison with attribute-level analysis, and strategic recommendations for defending and expanding narrative territory in AI responses
  • seo-specialist — 跨AI引擎回复的叙事分析、针对品牌档案的定位一致性评估、属性存在与失真检测、影响AI认知的引用策略、叙事修正的内容优化建议、强化知识源中准确品牌定位的结构化数据和实体更新指导
  • competitor-intelligence — 跨AI平台的竞争叙事追踪、品牌与竞争对手之间的叙事领地绘制、竞争对手抢占或丢失叙事主题的领地转移检测、基于属性层面分析的竞争定位对比，以及在AI回复中防御和拓展叙事领地的战略建议