Industry Deep-Dive Pipeline

Take a single technology / AI / data / cloud / enterprise-software topic from brief to an approved final Markdown. Uses Prompt Chaining + Evaluator-Optimizer: a fixed main chain guarantees traceability, and a revision loop after an eight-role panel review guarantees quality.

When to use

• The input is a topic brief, event, vendor case, policy change, or research material that needs a judgment-led, evidence-backed, boundary-clear deep-dive.
• You need to check Chinese and English coverage first to confirm information增量 (information gain) and phrasing-collision risk.
• You need pre-body planning of target reader, core judgment, argument chain, counter-arguments, structure, title, and risk.
• You need a complete evidence package: fact table, originality review, review record, and final-check.

Do not use

• News flashes, summaries, product manuals, tutorials, or marketing copy.
• Vendor conference panorama reports → use vendor-summit-report.
• LinkedIn single-platform short observations → use linkedin-industry-observation.
• WeChat layout, covers, summaries, keywords, social assets, CMS/Notion archiving or publishing → hand off to the independent publishing suite.
• Auto-scheduling or batch generation of multi-part series. Series info is context for a single article only.