Tag
The paper benchmarks email assistants across five communication-style axes and four English dialect variants, finding that indirect and formal requests degrade retrieval and cause agents to omit required actions rather than make unsupported ones, even when relevant evidence is successfully retrieved.
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 article highlights a wave of new plugins and tools for Hermes that enhance memory management, voice communication, email handling, and bot creation, positioning Hermes as a comprehensive operating system for AI agents.
Discusses the risk of auto-reply agents getting stuck in infinite email loops, and outlines practical guardrails such as checking auto-submitted headers, detecting no-reply senders, capping replies per thread, and using draft-first or human escalation modes.