Jamie Craane personal blog | Jamie Craane blog

Swapping OpenAI Embeddings for a Local Qwen3 Model

Same pgvector table, same 1536 dimensions, nothing leaves the machine

My knowledge base embedded every note with OpenAI's text-embedding-3-small. I added Qwen3-Embedding-8B served by LM Studio as a second, fully local option, without a new table or a re-index. Here is what that took: Matryoshka truncation, an instruction prefix for queries, and a model_id column.

Posted by Jamie Craane on Monday, September 14, 2026

Agentic Development Is Eating Low-Code

The friction low-code was invented to remove is the friction agents remove for free

Low-code traded boilerplate syntax for visual abstractions. Now that AI agents write the boilerplate, that trade no longer pays for itself. Here is where low-code breaks down, what changes with agents, and the narrow cases where low-code still wins.

Posted by Jamie Craane on Monday, August 31, 2026

Chunk Overlap Solves the Right Problem at the Wrong Time

Split on structure at ingest, and buy the context back at retrieval

Standard RAG advice says to overlap your chunks by 10 to 20 percent. My knowledge base uses zero overlap and expands a matched chunk to its enclosing section at query time instead. Here is why, and where it actually breaks down.

Posted by Jamie Craane on Thursday, July 23, 2026

Multi-Tenancy With Postgres Row-Level Security in Ktor

Enforcing tenant isolation in the database instead of in every query

How I use Postgres Row-Level Security, a non-owner application role, and a small Kotlin transaction wrapper to guarantee tenant isolation in a production Ktor and Exposed application.

Posted by Jamie Craane on Thursday, July 9, 2026

Parsing, Visualizing and Analyzing Log Data with Claude Code

From a static log file to an interactive analysis tool, and beyond

How I used Claude Code to turn a production slow-query log into an interactive visualization, then let Claude analyze the result and propose fixes.

Posted by Jamie Craane on Thursday, June 11, 2026

Operational Guardrails for Autonomous AI Agents in Production

Reliability Engineering in the AI Era

Defense in Depth practices for running autonomous AI agents safely — from least-privilege credentials and environment segregation to soft deletes, PITR, and RPO/RTO targets.

Posted by Jamie Craane on Thursday, April 30, 2026

Bridging Human Intent and AI Code Generation with @AIGuideline

A Novel Approach to Embedding Architectural Guidelines in Your Codebase

Learn how the @AIGuideline annotation helps AI assistants understand and respect your project's architectural decisions and coding patterns.

Posted by Jamie Craane on Monday, October 13, 2025

Integrating Firebase auth in server side Thymeleaf app

Using Firebase authentication with Ktor and Thymeleaf

This post, we will look at how to integrate server side Firebase authentication with Ktor and a Thymeleaf application

Posted by Jamie Craane on Thursday, June 12, 2025

Integrating Firebase JWT token verification in Ktor - Part 2

Using Firebase authentication with Ktor

This post, we will look at how to integrate your Firebase users in your own application database.

Posted by Jamie Craane on Wednesday, January 15, 2025

AI Assistant Prompt Catalog

Collection of useful prompts for Jetbrains AI Assistant

This blog post provides a collection of powerful prompts for JetBrains AI Assistant, designed to boost productivity and simplify development tasks. Perfect for Kotlin developers, it demonstrates how to leverage AI effectively within JetBrains IDEs.

Posted by Jamie Craane on Wednesday, December 11, 2024