Ivan Despot

Most teams treat documentation as the last mile: the feature ships, and then someone writes it up. By the time the docs get written, the API surface is frozen, the rough edges are baked in, and the person writing the docs is the least equipped to change any of it.

I've come to prefer the opposite order. Write the documentation first — or at least alongside the implementation — and let the act of explaining the feature shape the feature itself.

Getting a handful of objects into a vector database is easy. Getting millions in — reliably, without silently dropping data or melting your throughput — is where most ingestion pipelines start to hurt.

A coding assistant is only as good as the context you can feed it. This walkthrough builds one that retrieves over your own code and documentation using Weaviate's built-in MCP server.

Social networks are a natural fit for graph data: people are nodes, relationships are edges, and the questions you actually care about — who's central, which communities form, how information spreads — are questions about structure.

Hybrid search combines vector similarity with exact keyword matching — and the keyword half lives or dies by tokenization: how text gets broken into the discrete units that BM25 scores against.

"Add security later" is how most AI prototypes ship — and how they get stuck before production. This piece follows a fictional health-tech company from a single API key all the way to a compliance-ready setup.

Authentication and authorization get lumped together, but they answer different questions: who are you? and what are you allowed to do? Getting the second one right is what keeps a shared database from becoming a liability.