Category: Code

Chinese watercolor landscape with pagoda and misty mountains representing concurrent OpenAI calls and parallel orchestration powering iching.rocks I Ching readings

Firing 18 Concurrent OpenAI Calls: The Parallel Orchestration Behind iching.rocks Interpretations

Posted on February 20, 2026 by JB

When a user gets a paid reading on iching.rocks, the system needs to generate a comprehensive, multi-section I Ching interpretation. Not a single paragraph — a full document covering opening observations, hexagram judgments, changing line analyses, Ten Wings commentary, synthesis, and a conclusion. Each section requires its own carefully crafted prompt with injected domain data. […]

Read More: Firing 18 Concurrent OpenAI Calls: The Parallel Orchestration Behind iching.rocks Interpretations
Posted in Code
Digital wireframe skyscraper under construction on a circuit board representing persistent AI context and compounding development results with pgvector semantic knowledge system

From Theory to Proof: 9 Days With a Semantic Knowledge System in Production

Posted on February 19, 2026 by JB

Nine days ago, I published a post about building a semantic knowledge system — a pgvector-backed memory layer that gives every AI agent I work with persistent, searchable context across all my repositories. The architecture was clean. The idea was sound. But it was still mostly a promise. Nine days later, I have the receipts. […]

Read More: From Theory to Proof: 9 Days With a Semantic Knowledge System in Production
Posted in Code
AI brain visualization combining code snippets, database icons, and neural network connections representing a semantic knowledge system built with PostgreSQL pgvector and Model Context Protocol

Giving AI a Long-Term Memory: How I Built a Semantic Knowledge System Across Multiple Repos

Posted on February 10, 2026 by JB

AI coding assistants are powerful, but they have a fundamental limitation: they forget everything between sessions. Every new conversation starts from zero. Your agent doesn’t know what you built yesterday, what decisions you made last week, or why you chose Dapper over Entity Framework three sessions ago. I decided to fix that. Enter the Semantic […]

Read More: Giving AI a Long-Term Memory: How I Built a Semantic Knowledge System Across Multiple Repos
Posted in Code
C# and HashiCorp Vault logos overlaid on a stack of balanced stones representing a PKI certificate trust chain

Runtime Trust: Injecting a Private CA into .NET at Startup with HashiCorp Vault

Posted on February 5, 2026 by JB

Building Dynamic Trust Chains in C# Using Vault PKI Modern applications rarely live in isolation. Databases, APIs, message queues, and internal services all communicate over TLS—and in many organizations, those certificates are issued by a private Certificate Authority rather than a public one. This creates a subtle but critical challenge: how does a .NET application […]

Read More: Runtime Trust: Injecting a Private CA into .NET at Startup with HashiCorp Vault
Posted in Code
Angular frontend communicating with a headless WordPress backend via an API, shown on a developer’s desk setup.

Angular & Headless WordPress

Posted on January 29, 2026 by JB

If this works, I’m happy! One quiet afternoon, I sat down with a not-entirely-naive thought: Can I get an Angular frontend working against a headless WordPress backend? It was one of those ideas that seemed straightforward enough in theory — decouple the interface from WordPress’s theming system and drive the UI entirely from APIs — […]

Read More: Angular & Headless WordPress
Posted in Code