When I started building LLM applications, one thing became obvious very quickly: Getting a response...
Structured Output in LangChain
Related
frontier models are becoming cloud procurement
OpenAI and Codex showing up inside AWS is a reminder that enterprise AI adoption is often less about model access and more about billing, IAM, audit, and governance.
The AI judge that called a half-finished audit 'exhaustive'
If you're building anything with an LLM judge in the loop, this is the failure mode that will get...
Making the Context Across 46 Repositories Semantically Searchable for AI (Part 2)
The biggest issue Part 1 left open was that AI couldn't reach the 46-repo codebase by natural-language query (the entry-point problem). This post is how I solved it — by reusing th...