Claude Code Development

We Audit AI Visibility for a Living. So We Audited Ourselves.

Can you trust the score an AI visibility tool gives you, tomorrow as well as today? We test our own scoring weekly and audited our whole stack. Here is the proof.

Jul 22, 2026

Anthropic Agent SDK Hooks: TypeScript Reference

Programmatic Anthropic Agent SDK hooks reference. The core events, full TypeScript signatures, PreToolUse, PostToolUse, Stop, SubagentStop, UserPromptSubmit with worked examples.

May 23, 2026

Ghost Protocol: Multi-Agent Engineering Framework for GitHub Copilot

Ghost Protocol gives GitHub Copilot a team of 8 named specialist agents running 9 disciplined execution patterns. One installer script. Agents execute, leave clean results, disappear.

Apr 1, 2026

How We Built a Multi-Channel AI Sales Agent in One TBE Session

Case study: extending Vector from chat-only to email replies, broadcasts, and delivery tracking in a single Thread-Based Engineering session. Real code, real architecture.

Mar 25, 2026

Thread-Based Agentic Experience Engineering [TBE + AXD]

The unified framework connecting Thread-Based Engineering to Agentic Experience Design. How thread autonomy levels map to trust patterns and supervision models.

Mar 23, 2026

AI Product Development in the Philippines: Why Global CTOs Are Building Here

The Philippines AI development market is not about cheaper rates. It is about owned products, senior methodology-driven teams, and a timezone you can plan around. A practical evaluation framework for CTOs.

Feb 25, 2026

The Junior Developer Extinction Problem: Why AI Technical Debt Needs Human Apprentices

54% of engineering leaders plan to hire fewer juniors. The math looks right until you factor in who fixes AI-generated technical debt. A framework for CTOs rethinking their talent pipeline.

Feb 25, 2026

Your llms.txt Is Already Stale. Here's How to Fix It.

Static llms.txt files go stale the moment you publish new content. This guide covers what llms.txt actually does, why 844K sites got it wrong, and how to build a dynamic version in Next.js.

Feb 17, 2026

Claude Code Hooks: Corrections to Our February 2026 Guide (Dated Note)

A dated note on our February 2026 Claude Code hooks guide: why its config examples would not have worked, the correct shape from the official reference, and what we run instead.

Feb 14, 2026

Context Engineering Beyond CLAUDE.md: The 5-Layer Hierarchy

CLAUDE.md is just layer one. The five-layer context hierarchy, memory patterns, and subagent strategies that separate productive AI coding from prompt guessing. With working examples.

Feb 14, 2026

Slopsquatting and AI Supply Chain Attacks: A Defense Guide

AI tools hallucinate 19.7% of package names. Attackers register them as malware. Learn how slopsquatting works and layered defense strategies.

Feb 14, 2026

Lakbay AI: What We Built and What We Withdrew (Dated Note)

A dated note on our February 2026 Lakbay AI case study: what the travel concierge is, what its repository history shows, and the timeline, speed and security claims we withdrew.

Feb 8, 2026

Claude Code Technical Debt Mitigation: The Complete Production Guide

Prevent AI-generated technical debt with Claude Code using CLAUDE.md optimization, security-first prompting, and production guardrails. Research-backed strategies that deliver +5-10% improvement.

Feb 1, 2026

Thread-Based Engineering: How We Keep AI-Assisted Code Reviewable

How we govern AI-assisted development: two mandatory human checkpoints, the gates every change passes before it merges, and what the 2025 data says about AI code. As of October 2026.

Feb 1, 2026

84% of Developers Use AI Tools. 45% of AI Code Has Flaws.

84% of developers use or plan to use AI tools, yet only a third trust their accuracy, and 45% of AI-generated code samples failed security tests. The 2026 research data, the risks, and governance patterns that work.

Jan 31, 2026

Thread-Based Engineering: The Framework for Scaling AI Development

The definitive guide to Thread-Based Engineering: 7 thread types, governance alignment, a production case study (Lakbay AI), and the research on AI code quality, including the Veracode finding that models failed to write XSS-safe code 86% of the time.

Jan 24, 2026

The AI Copilot Stack Guide: Corrections and What We Withdrew (Dated Note)

A dated note on our 2025 AI copilot stack guide: the install commands and tool names that were wrong, the results and ROI figures we withdrew, and what we use today.

Sep 23, 2025