Tag
The article explores using email as a natural interface for asynchronous collaboration with AI agents, presenting the Machtiani project that integrates email into agent workflows.
The author argues that while LLMs make certain optimizations cheaper, software can still be slow due to factors like increased tolerance for latency in asynchronous workflows and other practical constraints.
The post discusses the evolution of Anthropic's Claude Tag from a single-user agent to an org-level harness in Slack, enabling multi-player collaboration, asynchronous work, and proactive behaviors through improved model capabilities and security.
This article presents nine Claude agents that run overnight to handle tasks like briefings, research, and inbox triage, allowing users to wake up to completed work. It provides instructions for setting up each agent using Claude Code, Claude.ai, or Claude Desktop.