Special Episode: Architecting Reliable Agentic AI I Cisco’s Giovanna Carofiglio on the AGNTCY Collective

Season 4 is almost here! In the meantime, we wanted to share an episode from our friends at Chain of Thought. It's a conversation with Cisco’s Giovanna Carofiglio about how you build the guardrails for this new world‌ — ‌how you let AI agents collaborate and create value, without creating chaos. 

As a leader of the AGNTCY Collective (an open-source initiative by Cisco, Galileo, LangChain, and many other participating companies), Giovanna outlines the vision for agents to collaborate seamlessly across the enterprise and the internet. She details the collective's pillars, from agent discovery and deployment using new agentic protocols like Slim, to ensuring a secure, low-latency communication transport layer.

This groundbreaking work aims to make distributed agentic communication a reality.

The conversation then explores the critical role of observability and evaluation in building

trustworthy agent applications, including defining an interoperable standard schema for

communications. Giovanna highlights the complex challenges of scaling agents to thousands or

millions, emphasizing the need for robust security (agent identity with OSF schema) and

predictable agent behavior through extensive testing and characterization. She distinguishes

between protocols like MCP (agent-to-tool) and A2A (agent-to-agent), advocating for open

standards and underlying transport layers akin to TCP.

AGNTCY Collective: agntcy.org

Connect with Giovanna on LinkedIn

Learn more about Outshift: outshift.cisco.com

Subscribe now so you don't miss Season 4 – out October 15! 

Learn more about WRITER at writer.com.