Context Engineering: The Core Skill Behind Production AI Agents
Why context engineering has become the defining skill for production AI agents in 2026 — 4 critical failure patterns and 5 core techniques, from an Engineering Manager perspective.
archive
Columns · Page 16
356 · Page 16
Karpathy's autoresearch: 100 Autonomous ML Experiments Overnight
Andrej Karpathy's autoresearch is a 630-line open-source tool that lets AI agents autonomously iterate ML experiments overnight. We analyze R&D team adoption strategies from an EM perspective.
LLMs Unmasking Anonymity — Reality of Large-Scale Identity Tracking
Analyzing large-scale online deanonymization research using LLMs and presenting organizational security defense strategies for engineering leaders.
AI Reliability Engineer and the Centaur Pod Model in 2026
Junior roles are evolving into AI Reliability Engineers. Centaur Pod team structures, Code Audit hiring, Defect Capture Rate — the AI-native team design brief for Engineering Managers.
Claude Found 22 CVEs in Firefox — AI Security Audits Arrive
Anthropic Claude Opus 4.6 discovered 22 CVEs in Firefox in just two weeks. We break down how AI-driven security audits work and what engineering leaders should do next.
Agent Scaling Science — Google Debunks 'More Agents = Better'
Google Research's 180-configuration experiment exposes the multi-agent paradox: 39–70% degradation on sequential tasks, 17.2× error amplification, and what it means for your architecture.
RoguePilot — Copilot Prompt Injection and AI Tool Security
Analysis of the RoguePilot vulnerability found in GitHub Codespaces, passive prompt injection risks in AI coding tools, and security guidelines for engineering teams.
A2A + MCP Hybrid Architecture: 2026 Multi-Agent Production Strategy
Google A2A and Anthropic MCP are complementary, not competing. An EM/CTO view of the two protocols' roles and strategies for running multi-agent systems safely in production.
Cursor Agent Trace — An Open Standard for Tracking AI-Generated Code
Analyze Cursor Agent Trace 0.1.0 specification and discover why AI code attribution tracking is critical for engineering leaders and CTOs beyond git blame.
Cut Agent Fleet Costs by 90% with Heterogeneous LLM Architecture
The Plan-Execute pattern: large models plan, small models execute. A practical guide for EMs and CTOs on heterogeneous LLM architecture strategies to dramatically reduce agent fleet costs without sacrificing quality.
Tool-R0: Self-Play RL for Tool-Using Agents, Zero Data
The arXiv paper Tool-R0 achieves 92.5% improvement in LLM tool-calling via Self-Play RL alone, with no training data. We analyze its Generator-Solver co-evolution and practical implications.
Bayesian Teaching: How LLMs Learn Probabilistic Reasoning
Google's Bayesian Teaching research, published in Nature Communications, introduces a training methodology that enables LLMs to probabilistically update their beliefs when receiving new information.