Precision Lives in the Second Stage: Reranking a Personal Knowledge Search with Claude
Embedding search alone leaves 'semantically close but not the answer' passages at the top. This is a two-stage design that gathers candidates broadly, then lets Claude reorder them by answerability, with structured scoring, abstention, and a cost estimate.
When the RAG Started Being Confidently Wrong — Field Notes on Measuring Retrieval Misses With Groundedness
In a Claude API RAG, the answers stay fluent while the facts drift. Often the cause is a silent recall decay on the retrieval side, missing the document that holds the answer. Field notes on measuring groundedness and retrieval hit rate and walking the system back, with working code and real numbers.
When Your Support AI Is Confidently Wrong in Production — Notes on Refusing Outside Its Grounding and Routing to Humans
A field-tested approach to the Claude API support agent that demos perfectly yet states non-existent facts in production. Covers deciding 'don't answer' at retrieval time, grounded generation, measuring confident-wrong rate, and tuning escalation precision.
Grounding Claude on Your Own Knowledge Base with search_result Blocks
How to stop your own RAG setup from losing track of which article it cited, using Claude's search_result content block and structured citations — with real numbers from running it across four sites.
Building an Internal Document Search Agent with Claude API — Hybrid RAG, Role-Based Access Control, and Audit Logging in Production
Build a production-grade internal document search agent using Claude API and Python. Covers hybrid RAG (pgvector + BM25), department-level RBAC via PostgreSQL RLS, and compliance-ready audit logging — with working code for each component.
Building a Persistent Memory Agent with Claude API, pgvector, and Redis: A Complete
A complete guide to building production-ready persistent memory for Claude API agents using PostgreSQL + pgvector + Redis. Learn vector search, layered memory architecture, session management, and GDPR-compliant data handling.
Building Production-Ready AI Apps with Claude API × Supabase — pgvector RAG, Realtime Sync & Row Level Security Integration Guide
Build production AI apps with Claude API and Supabase. Implement RAG with pgvector, multi-tenant RLS, and real-time streaming in one integrated architecture.
Building a Search-Augmented AI Assistant with Claude API: Web Search × Dynamic Filtering × Citations
Learn how to combine Claude API's Web Search Tool, Dynamic Filtering, and Citations API to build a production-grade search-augmented AI assistant that returns accurate, source-backed answers.