Blog
How I Improved an AI Agent from 40% to 60% — With A/B Test Data
Same model, same test cases, 20% better results. 7 out of 8 fixes were pure code, zero LLM cost. Here's exactly what I changed and why it worked.
[ AI_OPERATOR_—_BLOGS ]
Long-form writing on production AI agent engineering — validation loops, tool-call reliability, completion ownership, context engineering, cost forensics.
Other track:
SecurityLab — Blogs →
Blog
Don't Pick One AI. Run Three Against Each Other.
Don't bind to a single AI. Run three in competition, make the final call yourself, and let results judge everyone. The operating model for staying valuable in the AI age.
Blog
The 90% Problem: Why Most AI Agents Are Still Broken
Building an AI agent that works is easy. Building one that doesn't break is 90% of the work. Here's what that 90% actually looks like — from leaked source code and production A/B data.
Blog
Claude Code + Codex Plugin: Two AI Brains, One Terminal
How to use OpenAI's Codex plugin inside Claude Code — turning Claude Opus and GPT-5.4 into a dual-brain coding system. Setup, commands, rescue workflows, and when each brain wins.
Blog
Claude Code Deep Dive Part 4: Why It Uses Markdown Files Instead of Vector DBs
Claude Code's memory system looks simple on purpose. This piece breaks down the tradeoffs behind Markdown memories, Sonnet side-queries, and the decision to avoid vector databases.
Blog
Claude Code Deep Dive Part 3: The 5-Level Compression Pipeline Behind 1M Tokens
Claude Code doesn't just stuff conversations into a 1M-token window. It uses a 5-level compression pipeline, cache-aware edits, and a final autocompact fallback to keep sessions alive.
Blog
Claude Code Deep Dive Part 2: The 1,421-Line While Loop That Runs Everything
Inside query.ts — the 1,729-line async generator that is Claude Code's beating heart. 10 steps per iteration, 9 continue points, 4-stage compression, and streaming tool execution. With line numbers.
Blog
Observability and Billing for AI API Calls: A T-Shaped Architecture
AI API calls are unlike ordinary RPC: per-request cost varies 100×, tokens and models are first-class, streaming muddies timing, caching changes the pricing. A T-shaped instrumentation architecture — shared stem, specialized arms — that handles tracing, billing, and cost analytics without any of them contaminating the others.
Blog
Claude Code MEMORY.md Spec: The 4 Frontmatter Types Decoded (user / feedback / project / reference)
The MEMORY.md frontmatter spec from Claude Code's leaked source: 4 types (user, feedback, project, reference), 200-line index cap, LLM-based picker. What's right, where it breaks at scale.
Blog
Claude Code Source Leaked: Kairos, Undercover Mode, Ultraplan — 5 Hidden Features (510K Lines)
Claude Code v2.1.88 accidentally exposed 510K lines. The 5 hidden features: Kairos (permanent memory), Undercover Mode (stealth), Ultraplan (deep planning), Pet System (Buddy), Multi-Agent. Source-cited.