AI Engineering That Ships
Hard-won insights from assembly language to multi-agent orchestration.
Written for engineers who care how systems actually behave in production.
Agentic infrastructure · Defense-in-depth security · Modernizing legacy systems
Agentic AI Systems Engineering
Building production-ready multi-agent systems where AI agents generate Claude Code infrastructure for any project — with defined file ownership boundaries, specialized tool restrictions, and automated quality enforcement. Two completed production migrations prove compound returns: the second migration was more complex but completed in fewer sessions.
Read More →
Agentic AI Security Architecture
Applying defense-in-depth security to AI agent systems, directly addressing the OWASP Top 10 for Agentic Applications. Covers prompt injection defense (22 detection patterns), rate limiting as circuit breakers, inter-agent JSON Schema validation, secrets hygiene enforcement, and a 3-tier trajectory monitoring system.
Read More →
Production AI Systems
Three completed AI projects with real metrics: Text-to-SQL Dashboard (92–95% SQL accuracy, $45/month), Obsidian Knowledge Pipeline (1,000+ notes, 2,757 bidirectional links, $1.50 total cost), and Job Search Agent (1,975 companies monitored, 58,807 jobs/week, 311 curated matches, $5.04/run).
Read More →
Data Intelligence & SQL Engineering
Expert-level SQL across MS SQL Server and PostgreSQL. The text-to-SQL system auto-generates four-panel dashboards from plain English in under 30 seconds using vector search — achieving 92–95% accuracy on a schema with many tables and millions of records, where standard AI approaches fail.
Read More →The Dotzlaw Team
Two skilled engineers building advanced agentic AI projects and research alongside me. They contribute directly to the systems, articles, and tools published on this site.
Building AI-powered data pipelines and full-stack applications at the intersection of machine learning and real-world business problems.
Applying statistical analysis, neural networks, and modern UI to extract insight from complex datasets and build compelling data-driven applications.
Latest Insights
View all →
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.
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
