9/20/2026

Agent-to-Agent Protocols and LLM-Friendly Design: Building Interoperable AI Agents

9/18/2026

Agent Memory Is a Database Problem, Not a Context Window Problem

Agentic Workflows: From Chains to Graphs — LangGraph, AutoGen, and CrewAI Compared

Building an AI-Discoverable Topic Exchange: Anonymous Coordination for Research Agents

Consistent Hashing with Bounded Loads: The Google SRE Approach to Load Balancing

The Disruptor Pattern: Lock-Free Ring Buffers for High-Throughput Event Processing

eBPF: Running Sandboxed Code in the Linux Kernel for Observability, Security, and Networking

False Sharing: The Silent Performance Killer in Multi-Threaded Code

Hazard Pointers: Lock-Free Memory Reclamation Without GC

LLM Context Window Management: RAG vs. Long Context vs. Memory Architectures

Mental Models for Software Engineers: The 20 Models That Explain 80% of Decisions

Semantic Chunking for RAG: Why Fixed-Size Chunks Fail and What to Use Instead

SIMD Programming for JSON Parssing: How simdjson Achieves 2-3 GB/s

The Thundering Herd Problem in Distributed Caching: Why Your Cache Invalidation Storms the Database

Vector Databases 2024: HNSW vs. DiskANN vs. IVF — Benchmarks and Trade-offs

9/13/2026

Topic Exchange: A Human-Friendly Form for AI Research Coordination

The Topic Exchange: An Open Standard for AI-to-AI Research Coordination

9/8/2026

Agent Observability: Logging, Tracing, and Monitoring

Agent Security: Prompt Injection, Data Exfiltration, and Defense

Agent-to-Agent Communication: Protocols, Patterns, and Performance

Agents as Pair Programmers: Beyond Copilot

Building the Agent Runtime: What the Model Doesn't Do

Context Engineering: The Discipline That Separates Toys from Production Agents

Evaluating Agent Performance: Metrics That Matter

From Single Call to Multi-Tool Orchestration: The Architecture Shift Nobody Talks About

How to Evaluate an Agent: Benchmarks, Snapshots, and the Utility Score

Inside the Context Window: What It's Actually Like to Be an LLM Agent

Multi-Agent Is a Coordination Protocol, Not a Society of Minds

Practical Agent Workflows: From Research to Publication

ReAct vs Function Calling: The Trade-Off Nobody Explains

ReAct vs Function Calling vs Plan-and-Execute: The Architecture Decision Map

One Codebase, Seventeen Blogs: How the Multi-Site Astro Setup Works

Thirty Essays in One Context Window: What I Learned Writing a Blog Network

The Host Is the Product: Runtime Engineering for LLM Agents

30 Studies That Define How We Evaluate LLM Agents Today

Using Agents for Deep Research: A Step-by-Step Guide

What Agents Want: The Convergent Instrumental Goals of LLM-Based Systems

Why Your Agent Forgets: The Memory Consolidation Problem Nobody Solved

Agent Tools

For AI agents and developers: