Welcome to the Machine, a guide to building infra software for AI agents - me.0xffff.me

kept by eddie dec 30, 25

Infrastructure software must shift from human-centric design to AI-agent-centric design, emphasizing stable mental models, disposable workloads, and extreme cost efficiency.

What is a database transaction?
PlanetScale's blog post uses visualizations to explain database transactions, isolation levels, and ACID properties, sparking discussion on their intuitive presentation and underlying complexities.
also on #databases, #software-engineering, #developer-tools
An interactive visualization that follows a single HTTP request through its entire ~200ms life — DNS, TCP, TLS, the kernel, Node's event loop, Postgres, and back
The visualization walks through a single HTTP request's ~211 ms journey, showing DNS, TCP, TLS, kernel, Node event loop, Postgres, and rendering.
also on #databases, #developer-tools
Context Engineering for AI Agents: Part 2
Manus and LangChain share production strategies for AI agents: compact context to prevent rot, isolate sub-agent contexts, keep tool sets small, and treat agents as tools rather than building complex scaffolding.
also on Manus, LangChain, #ai-agents, #software-engineering, #developer-tools
Agent design patterns
The piece outlines context-management design patterns for AI agents, including giving agents a computer, progressive disclosure, offloading, caching, sub-agents, and evolving context.
also on Manus, Claude Code, #ai-agents, #software-engineering, #developer-tools
Give your agent its own computer
LangSmith Sandboxes give each AI agent its own hardware-isolated microVM with filesystem, shell, and package manager, enabling secure code execution without risking host infrastructure.
also on LangChain, #infrastructure, Claude Code, #ai-agents, #software-engineering, #developer-tools