Explores zero-ETL federation as a real-time data access method for AI agents, replacing batch ETL to enable live cross-enterprise analytics.
Fleet is a terminal dashboard for managing multiple Claude Code sessions in tmux, prioritizing agents that need human attention.
Article discusses the security risks of 'vibe coding' with AI and offers strategies to secure AI-generated applications.
Tutorial on building an AI agent with Pydantic AI to generate cold emails based on company websites.
Armin Ronacher explains why he uses 'clanker' instead of 'agent' for AI tools, emphasizing machines as tools without agency.
How incident.io uses interlocks to prove Claude read skill files before calling tools, improving AI agent reliability.
Armin Ronacher reflects on using AI agents (Pi) to build Pi, highlighting challenges with AI-generated bug reports.
Explores using AI agents to automate parts of qualitative analysis, specifically grounded theory, with experimental setups varying human involvement.
Analysis of a real-world account takeover attack, highlighting how AI agents enable fast, coordinated credential stuffing and the new economics of cybercrime.
Learn how to use a second AI agent to critique and catch flaws in AI-generated plans before building, based on the Reflexion pattern.
Explores four subagent patterns in AI agent systems for 2026, focusing on agent management and task delegation.
An article on building a personal identity through documented history and using AI agents while maintaining human authenticity.
Explores designing autonomous AI agent teams for software engineering, from subagents to parallel implementations.
Explores the end of traditional coding, shifting from writing syntax to expressing intent and leading AI agents in software development.
Summary of a fireside chat at Sequoia Ascent 2026 discussing AI agents, Software 3.0, and the shift to agentic engineering.
Practical advice on implementing AI in software development, focusing on boring but valuable workflows, safety guardrails, and real-world delivery over hype.
Learn two proven patterns for correctly using MCP servers with AI agents to avoid context bloat, higher costs, and poor performance.
Guide to hosting an AG-UI agent on Microsoft Foundry, covering setup, protocols, and managed endpoints.
Analysis of Anthropic's Mythos model, Vercel breach, and AI red teaming, plus Claude Code's new cyber content restrictions.
Anthropic's postmortem on Claude Code quality issues reveals three bugs affecting user sessions, including a memory-clearing bug causing forgetfulness.
