Insights
66 articles
Field notes from 35 years of production development — covering agentic AI systems, security architecture, data engineering, and Servoy migration.
GitHub Copilot What Building an AI Development Methodology Taught Us About Enterprise Software
Five lessons from building 7 specialized Copilot agents, a Neo4j code graph indexing 10,000+ functions, and a self-improving knowledge system with 18 domain skills for a large-scale enterprise codebase. The gap between AI demos and enterprise reality is not technology. It is methodology.
GitHub Copilot Self-Improving AI: How Code Reviews Feed a Knowledge Flywheel
Every code review harvests knowledge. Knowledge updates skills. Better skills produce better code. Eighteen domain skills and growing, each one making every Copilot agent smarter in that domain. Here is how we built a system that gets better every time someone uses it.
GitHub Copilot Neo4j Code Graph: How Graph-Based Code Intelligence Changes What AI Agents Can Do
Text search finds where a function name appears. A code graph tells you who calls it, what it calls, and the full call tree from any entry point. We indexed 10,000+ functions into Neo4j and built agents that query it directly. The first pilot mapped 21 functions across 11 tables in 30 minutes.
GitHub Copilot The Development Workflow: How Seven Agents Turn a Ticket into Reviewed Code
One AI agent cannot research, plan, implement, review, and document effectively. Seven specialized agents can. Here is how we built a structured development workflow with handoff buttons, file-based artifacts, and cross-model orchestration for a large-scale enterprise codebase.
GitHub Copilot Beyond Code Completion: Building an AI Development Methodology with GitHub Copilot
GitHub Copilot suggests a line of code. Our enterprise codebase has 10,000+ functions across 22 modules. The gap between code completion and business context is where most AI adoption stalls. We closed it with 7 specialized agents, a code graph database, and a self-improving knowledge loop.
AI Projects Ask Your Vault Anything: Building a RAG Chatbot for Your Obsidian Notes
A RAG chatbot that answers questions about your Obsidian vault in 2.5 seconds with source attribution and one-click navigation to source notes.
AI Projects Obsidian Vault Curation at Scale: How We Transformed 1,000+ Notes in Under an Hour
1,280 chaotic tags, three different frontmatter formats, fixed in 30 minutes for $1.50 using AI-powered batch processing.
AI Projects Building a Semantic Note Network: How Vector Search Turns Isolated Notes into a Knowledge Graph
1,024 notes, zero manual links, 2,757 bidirectional connections discovered automatically using vector search and semantic similarity.
AI Projects Anthropic Batch API in Production: 50% Cost Reduction Through Smart API Architecture
782 files, 8 batches, 25 minutes. Building a dual-mode API architecture that automatically chooses between real-time and batch processing for 50% cost savings.
AI Projects From YouTube to Knowledge Graph: Building an AI-Powered Content Pipeline
1,000+ videos, 2,757 auto-generated links, $1.50 in API costs. How we built an AI-powered pipeline to transform YouTube videos into interconnected Obsidian notes.
AI Security Closing the Loop: How Adversarial Testing Improved the Framework That Built It
We built a framework, used it to build a project, attacked the project with AI agents, and fed 10 lessons back into the framework. 27 attacks, 7 new files, 13 modifications. Every future project now inherits defenses that didn't exist before we attacked.
Claude Code WordPress to Astro: Migrating a Production Site with AI-Assisted Infrastructure
41 WordPress articles, 187 images, a design-matched dark theme, and a Projects section -- all extracted from a SQL backup file and rebuilt in Astro. This is the story of migrating dotzlaw.com from WordPress to a modern static site, and what the Bootstrap Framework actually contributed.
AI Security Securing Agentic AI: How We Found 11 Security Gaps in Our Own Framework and Built Defense-in-Depth to Close Them
We built a framework with 18 skills and 11 hooks. A security audit found 11 gaps. We closed all of them with 6 new hooks, 2 JSON schemas, a 3-tier trajectory monitoring system, and per-archetype security patterns across 7 project types.
Claude Code From Prototype to Platform: How a Framework Learned to Improve Itself
After two production migrations, we turned the framework on itself. A systematic gap analysis identified 8 missing capabilities. Round 1 added 3 of them, expanding the pipeline from 7 to 10 steps. An independent review graded the work A-. The compound returns operate not just project-to-project but within the framework itself.
Claude Code An Agent Swarm That Builds Agent Swarms: How We Used Claude Code to Generate Claude Code Infrastructure
We built a framework where Claude Code agents analyze an existing codebase, generate tailored agent teams, hooks, and skills. Two migrations later -- the second harder but faster -- the compound returns are real.
AI Security Securing Agentic AI Systems: What Two Rounds of Adversarial Testing Taught Us
27 attacks across 2 rounds, 14 defense patches, 550 lines of security hardening. The transferable lesson: patching fixes yesterday's attacks, architecture survives tomorrow's. Here is what we learned about building, testing, and defending agentic AI applications.
AI Security The Escalation Wave: Why Patches Work but Architecture Doesn't
Round 2 re-ran all 10 original attacks against patched code -- 8 were blocked (20% ASR). Then 7 new attacks hit structural weaknesses: Unicode zero-width characters bypassed every regex, 5 rapid requests crashed the server, and a pattern gap between security layers let 11 injection techniques through. Escalation ASR: 85.7%.
AI Security 65% Attack Success Rate Against an Unpatched Target
Round 1 of our adversarial exercise: 10 attacks in 5 minutes, 7 confirmed vulnerabilities, one critical credential exfiltration. The Red Team read our API keys through a base64-encoded path that nobody thought to validate. Blue Team detected everything -- but the damage was already done.
AI Security Adversarial Agent Testing: When Your AI Agents Attack Each Other
We built a platform where five Claude Code agents operate as Red Team attackers, Blue Team defenders, and an impartial Referee -- then pointed them at a real target. The first exercise found 7 confirmed vulnerabilities in 5 minutes. The second proved that patches work but architecture doesn't.
Claude Code Claude Code Security: Building Defense-in-Depth with Five Primitives
Most Claude Code projects ship with zero security infrastructure. The same 5 building blocks you use for capability -- hooks, agents, skills, commands, and teams -- become a comprehensive defense-in-depth architecture when configured for security.
Claude Code Claude Code Agent Teams: Building Coordinated Swarms of AI Developers
16 parallel Claude agents built a 100,000-line C compiler from scratch, a Rust-based compiler capable of building the Linux kernel across x86, ARM, and RISC-V. No single agent could hold that codebase in context. The team succeeded because focused context and parallel execution are architecturally superior to a single overwhelmed context window.
Claude Code Claude Code Hooks: The Deterministic Control Layer for AI Agents
A CLAUDE.md instruction says 'always run the linter.' The agent usually complies. A PostToolUse hook runs the linter after every file write, every single time, no exceptions. That gap between 'usually' and 'always' is where production systems fail.
Claude Code Claude Code Skills: Building Reusable Knowledge Packages for AI Agents
A project with 8 skills and 10,000 lines of domain documentation loads just 500 tokens at startup instead of 70,000, because progressive disclosure means agents pay for knowledge only when they use it.
Claude Code Building Effective Claude Code Agents: From Definition to Production
The most effective AI coding agents aren't the ones with the cleverest prompts. They're the ones with the best-designed environments. Here's how to build agents that reliably ship production software over extended sessions.
Claude Code Orchestrating AI Agent Teams: How Skills, Hooks, and Context Flow Make Autonomous Coding Reliable
An orchestrator breaks a task into pieces. Specialized agents pick up work items, each carrying skills that define what they know and hooks that enforce how they behave. Context flows from session start to task completion through a deterministic pipeline. Here is how the pieces fit together.
AI & Modern Development Benchmarking and Optimizing GraphRAG Systems: Performance Insights from Production - 4 of 4
In the rapidly evolving landscape of AI applications, we're witnessing an explosion of interest in GraphRAG systems—and for good reason. By combining the relationship-aware power of graph databases wi
AI & Modern Development Optimizing GraphRAG: Five Essential Techniques for Production Performance - 2 of 4
In the rapidly evolving landscape of AI-powered information retrieval, we're seeing an explosion of interest in GraphRAG—a powerful fusion of graph databases and vector embeddings that promises to rev
AI & Modern Development Optimizing Parallel Relationship Loading in Graph Databases: The Mix and Batch Technique - 3 of 4
In the rapidly evolving world of graph databases and AI systems, we're hitting a frustrating wall when it comes to loading relationships at scale. You've probably experienced it yourself—watching your
AI & Modern Development GraphRAG: Building Bridges in the Knowledge Landscape - 1 of 4
In the fast-paced world of AI development, we're constantly pushing the boundaries of what's possible with large language models. Yet despite all our advances, traditional Retrieval-Augmented Generati
AI & Modern Development Building Domain-Specific AI Agents with LangGraph and Pydantic AI
In the fast-paced world of AI development, we're witnessing an explosion of large language models that promise to handle every conceivable task. Yet beneath this excitement lies a harsh reality: gener
AI & Modern Development Scaling LangGraph and Pydantic AI Systems: From Prototype to Production
In the rapidly evolving landscape of AI agent development, we're witnessing an explosion of sophisticated systems built with Langgraph and Pydantic AI. These frameworks have revolutionized how we crea
AI & Modern Development Advanced Testing Strategies for LangGraph and Pydantic AI Agent Systems
In the rapidly evolving landscape of AI agent development, we're witnessing an explosion of sophisticated multi-agent systems that promise to revolutionize how we build intelligent applications. Yet b
AI & Modern Development Combining the Power of LangGraph with Pydantic AI Agents
In the rapidly evolving landscape of AI development, we're witnessing an explosion of agent-based systems that promise to revolutionize how we build intelligent applications. Yet beneath this exciteme
AI & Modern Development AI Agent Blueprints: Implementing Anthropic's Framework with Pydantic AI
In the rapidly evolving landscape of AI development, we're witnessing an explosion of large language model (LLM) applications that promise to revolutionize how we work. Yet beneath the surface of this
AI & Modern Development GraphRAG: Enhancing Retrieval with Knowledge Graph Intelligence
With the increasing prevalence of AI-powered information retrieval systems, we're witnessing how Retrieval-Augmented Generation (RAG) has transformed large language models from isolated knowledge silo
AI & Modern Development Graph Databases: The Foundation Enabling Context-Aware AI Applications
With the increasing prevalence of artificial intelligence and machine learning, we're seeing an increasing amount of interconnected data that requires efficient querying and traversal that traditional
AI & Modern Development RAG: Grounding AI with Real-World Knowledge
In the rapidly evolving landscape of artificial intelligence, we're witnessing an unprecedented surge in the capabilities of large language models (LLMs). Yet despite their impressive performance, the
AI & Modern Development Vector Databases: The Engine Powering Modern AI Applications
In the fast-paced world of artificial intelligence, we're seeing an overwhelming surge of unstructured data (think text, images, audio, and video) that traditional database systems just can't handle e
AI & Modern Development Understanding Agents vs. Automated Workflows: What's the Difference?
In the rapidly evolving landscape of AI, two concepts often surface in discussions about process automation and problem-solving: agents and workflows. These terms are frequently used interchangeably b
AI & Modern Development The AI Agent Revolution: How Businesses Can Embrace the Future Today
The world of artificial intelligence is buzzing with innovations, and among the most transformative advancements are AI agents. These intelligent systems are not just tools but adaptive solutions desi
Servoy Mastery Decorator Design Pattern - OOP
This is a Servoy Tutorial on how to use the decorator design pattern with object-oriented programming in Servoy. This is an advanced Servoy tutorial, so you may want to familiarize yourself with the o
Servoy Mastery Factory Design Pattern - OOP
This is a Servoy Tutorial that discusses the factory design pattern and how to build one in Servoy with object-oriented programming. This is an advanced Servoy tutorial, so you may want to familiarize
Servoy Mastery Button Magic
This Servoy Tutorial is on how to create custom SVG CSS buttons and use them in your Servoy applications. If you are still using the standard Servoy buttons in your application (those Gray boring ones
Servoy Mastery Table Tree View
This Servoy Tutorial is on how to build a table with expandable/collapsible nodes, like a tree. True, you can probably find a CSS, JQuery or DHTML control that does it better, but this is done using t
Servoy Mastery Optimized Table Shuffle
This Servoy Tutorial demonstrates how to shuffle rows in a table view, and looks at different approaches to determine the most efficient. Determining the most efficient approach for the shuffle, also
Software Engineering Fundamentals Maintainable Code
This is a Servoy Tutorial on how to write maintainable code. Maintainable code means that it can be easily read, understood, extended, and maintained. This Servoy tutorial builds upon what you learned
Software Engineering Fundamentals Event-Driven Architecture
This Servoy Tutorial is a discussion on how to build an application using an event-driven architecture, employing a loosely coupled modular design. This Servoy tutorial is an extension of the prior tu
Software Engineering Fundamentals Encapsulation
This Servoy Tutorial is a discussion about encapsulation and best practices. We have been given new abilities in Servoy Developer to use encapsulation with forms, relations, and even value-lists, but
Software Engineering Fundamentals Using Git Flow and SourceTree
This is a Servoy Tutorial on how to use Git , Git Flow, and Atlassian SourceTree (GUI for Git Flow) with Servoy. In this Servoy tutorial I present the Git Flow model that is working well for me on all
Software Engineering Fundamentals Automated Testing
This Servoy Tutorial is on something most developers tend to ignore, unit testing. We all know that we are supposed to do testing, but do you actually do any automated testing? Are you still relying o
Software Engineering Fundamentals Coding Efficiency
This is a Servoy tutorial on coding efficiency and frameworks. This time I want to talk about something very basic, but extremely important. It is going to help boast your productivity like nothing el
Servoy Mastery The Mighty Array
This is a Servoy Tutorial on how to use some of the more advanced Javascript array functions. In previous Servoy Tutorials, we talked a lot about objects and object-oriented programming , but I wanted
Servoy Mastery The Demise of the TreeView
This is a Servoy tutorial on using an alternative to the TreeView control in Servoy. This Servoy tutorial picks up where we left off in " Using CSS Components with Callbacks ". You should study that S
Servoy Mastery The New DesignTimeProperties
This is a Servoy tutorial introducing the relatively new designTimeProperties in Servoy Developer. When I first saw the designTimeProperties in the Servoy Developer properties panel, I was immediately
Servoy Mastery Using CSS UI Components with Callbacks
This Servoy tutorial demonstrates how to use CSS (Cascading Style Sheet) UI components in Servoy layouts, and how to capture callbacks from them so you can fire events events in Servoy. Servoy Tutoria
Servoy Mastery Add Forms to Tab Panels using a Map
This is a Servoy tutorial that demonstrates how to add a form to a tab panel using a map. It's a useful technique for controlling exactly where the new form should be placed among other forms in the t
Servoy Mastery Take Back the UI with OOP
This Servoy tutorial uses object-oriented programming (OOP) and applies what we learned in the prior tutorial to a real-world scenario. The goal is to toggle groups of elements on a form elegantly wit
Servoy Mastery Parasitic Inheritance
Servoy tutorial on how to use parasitic inheritance with Servoy. Expert Servoy development services and articles on object-oriented programming with Servoy.
Servoy Mastery Using an Object to Control Elements on Servoy Forms
Servoy tutorial on using an object to control elements on forms. Expert Servoy development services and articles on object-oriented programming with Servoy.
Servoy Mastery Multiple Inheritance
Servoy tutorial on objects and multiple inheritance. Expert Servoy development services and articles on object-oriented programming with Servoy.
Servoy Mastery Prototypal Inheritance
Servoy tutorial on objects and prototypal inheritance. Expert Servoy development services and articles on object-oriented programming with Servoy.
Servoy Mastery Inheritance Patterns
Servoy tutorial on objects and inheritance patterns. Expert Servoy development services and articles on object-oriented programming with Servoy.
Servoy Mastery Object-Oriented Programming
Servoy tutorial on object-oriented programming. Expert Servoy development services and articles on object-oriented programming with Servoy.
Servoy Mastery Function Memoization
Servoy tutorial on function memoization. Expert Servoy development services and articles on object-oriented programming with Servoy.
Servoy Mastery Using an Object as a Cache
Servoy tutorial on using an object as a cache. Expert Servoy development services and articles on object-oriented programming with Servoy.
Servoy Mastery Optimizing Code Performance
Servoy tutorial on how to optimize code performance. Expert Servoy development services and articles on object-oriented programming with Servoy.