3+ week, 6+ day ago   (1680+ words) A one-shot pipeline commits to its first try: parse once, retrieve once, generate once, return whatever comes out. When retrieval comes back empty or the answer is half-formed, there is no second chance. A loop gives the pipeline one: notice…...

2+ week, 4+ day ago   (1842+ words) Enterprise Document Intelligence [Vol.1 #14C] - One hour with two people, six to ten fields, and the two signals that separate a real column from one that will break a filter later A lot of RAG work right now goes into letting…...

2+ week, 5+ day ago   (1470+ words) Enterprise Document Intelligence [Vol.1 #M3] – The ten positions the series argues from, and the map of every article that argues them This article is a manifesto of Enterprise Document Intelligence, a series that builds an enterprise RAG system from four bricks....

3+ week, 21+ hour ago   (833+ words) LoRA fine-tuning solved our under-labeling problem. Whether it makes sense for you depends on three questions. Image classifiers can be built in many ways. The modern default approach is to run images through a third-party API which internally uses a…...

3+ week, 1+ day ago   (928+ words) Enterprise Document Intelligence [Vol.1 #7sexies] – The unit of retrieval doesn’t have to be a page or a paragraph. When the corpus carries tables, each body row with its column headers is a chunk in its own right, and it’s often the…...

3+ week, 2+ day ago   (1731+ words) Why retrieval quality should be a property of the system, not of the question's wording? Rebuilding knowledge layer with graph traversal on every query, bitemporal edges, and two-threshold entity resolution. The architecture held up. The contradiction register refused to answer…...

3+ week, 3+ day ago   (1857+ words) A controlled comparison of a top-5 RAG pipeline and a full 127,000 token prompt on the same 12 questions, same system prompt and same model. Graded blind on correctness, completeness and grounding. When Kimi K3 came out in July with a context window…...