2+ day, 15+ hour ago   (1738+ words) I built a system that automatically discovers, verifies, and applies relevant requirements from earlier interactions without asking the user where they came from. I built a complete, working implementation in pure Python and shared actual benchmark numbers from real runs…...

1+ week, 5+ day ago   (1817+ words) What each one solves, and runnable code you can paste into a notebook. Anyone can now build an LLM demo with a single API call. Getting that same feature to survive real users, real data, and a real bill is…...

1+ week, 6+ day ago   (1426+ words) What I learned after thinking more carefully about Structured Outputs on messy, incomplete data Three weeks after I turned on Structured Outputs for a pipeline that parsed payment confirmation messages into transaction records, I noticed that our reconciliation job started…...

4+ week, 34+ min 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, 1+ day ago   (1306+ words) Blueconic sets this cookie as a unique identifier for the BlueConic profile. Four skills worth adding to your workflow today if you don't want to be left behind A couple months ago I wrote about 3 Claude skills every data scientist…...

2+ week, 5+ 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…...

3+ week, 1+ day 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, 3+ 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, 4+ day ago   (1069+ words) A production account of the throughput work behind a 16x jump — and the two guarantees it was never allowed to trade away Two guarantees sat underneath every throughput change, and every one of the optimizations later in this article is built…...

3+ week, 5+ day ago   (1671+ words) I expected adding more communication pathways between agents to dramatically change network performance. It didn't. Figuring out why turned into a more useful article than the one I set out to write. This article shows a full working implementation in…...