The authors (MIT's Project NANDA) are really pro-LLM, hoping to develop an "Internet of AI Agents." Unsurprisingly, their recommendations on how organizations should integrate LLMs involve embracing their NANDA platform:
> The window for crossing the GenAI Divide is rapidly closing. Enterprises are locking in learning-capable tools. Agentic AI and memory frameworks (like NANDA and MCP) will define which vendors help organizations cross the divide versus remain trapped on the wrong side ... The infrastructure to support this transition is emerging through frameworks like Model Context Protocol (MCP), Agent-to-Agent (A2A), and NANDA, which enable agent interoperability and coordination. These protocols create market competition and cost efficiencies by allowing specialized agents to work together rather than requiring monolithic systems.
> The window for crossing the GenAI Divide is rapidly closing. Enterprises are locking in learning-capable tools. Agentic AI and memory frameworks (like NANDA and MCP) will define which vendors help organizations cross the divide versus remain trapped on the wrong side ... The infrastructure to support this transition is emerging through frameworks like Model Context Protocol (MCP), Agent-to-Agent (A2A), and NANDA, which enable agent interoperability and coordination. These protocols create market competition and cost efficiencies by allowing specialized agents to work together rather than requiring monolithic systems.