<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Nie Er | AI Delivery Notes (AILDNC) Articles</title><description>Articles by Nie Er on enterprise RAG, document parsing, information extraction, AI agent workflows, and LLM application delivery from AILDNC.</description><link>https://www.aildnc.com/</link><language>en</language><item><title>Contract Extraction Needs Evaluation, Not Just Prompt Tweaks</title><link>https://www.aildnc.com/en/blog/contract-extraction-evaluation/</link><guid isPermaLink="true">https://www.aildnc.com/en/blog/contract-extraction-evaluation/</guid><description>Reliable contract extraction requires golden sets, field-level checks, evidence validation, error attribution, and version comparison.</description><pubDate>Thu, 04 Jun 2026 00:00:00 GMT</pubDate></item><item><title>In Investment Research RAG, Query Understanding Is Easier To Underestimate Than Vector Search</title><link>https://www.aildnc.com/en/blog/rag-query-understanding/</link><guid isPermaLink="true">https://www.aildnc.com/en/blog/rag-query-understanding/</guid><description>In real investment research Q&amp;A, RAG quality depends less on vector search alone and more on coreference, time range, entity recognition, tag filters, and evidence boundaries.</description><pubDate>Thu, 04 Jun 2026 00:00:00 GMT</pubDate></item><item><title>Why Macro Report Generation Should Not Let LLMs Improvise</title><link>https://www.aildnc.com/en/blog/structured-llm-reporting/</link><guid isPermaLink="true">https://www.aildnc.com/en/blog/structured-llm-reporting/</guid><description>Financial and macro report generation needs engineered data cadence, traceable sources, explicit disagreement, structure, and refusal behavior.</description><pubDate>Thu, 04 Jun 2026 00:00:00 GMT</pubDate></item></channel></rss>