Architecting Reliable Agentic AI | Cisco’s Giovanna Carofiglio on the AGNTCY Collective

https://is1-ssl.mzstatic.com/image/thumb/Podcasts221/v4/1a/72/64/1a726482-7083-a5cc-8297-64a41bf00914/mza_14516134343677659949.jpg/600x600bb.jpg

Chain of Thought

Galileo + Conor Bronsdon

43 episodes

4 days ago

Introducing Chain of Thought, the weekly podcast for software engineers and leaders that demystifies artificial intelligence. Join host Conor Bronsdon each week as we tell the stories of the people building the AI revolution, unravel actionable strategies for agents and share practical techniques for building effective GenerativeAI applications.

Technology

RSS

All content for Chain of Thought is the property of Galileo + Conor Bronsdon and is served directly from their servers with no modification, redirects, or rehosting. The podcast is not affiliated with or endorsed by Podjoint in any way.

Technology

https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_nologo/42310277/42310277-1748630694291-4f161b64beb06.jpg

Architecting Reliable Agentic AI | Cisco’s Giovanna Carofiglio on the AGNTCY Collective

Chain of Thought

41 minutes 2 seconds

4 months ago

Architecting Reliable Agentic AI | Cisco’s Giovanna Carofiglio on the AGNTCY Collective

The Internet of Agents is rapidly taking shape, necessitating innovative foundational standards, protocols, and evaluation methods for its success.

Recorded at Cisco's office in San Jose, we welcome Giovanna Carofiglio, Distinguished Engineer and Senior Director at Outshift by Cisco. 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.

Chapters:

00:00 Introduction

01:00 Overview of Agent Interoperability

02:20 What is AGNTCY

03:45 Agent Discovery and Composition

04:38 Agent Protocols and Communication

05:45 Observability and Evaluation

07:00 Metrics and Standards for Agents

09:45 Challenges in Agent Evaluation

14:15 Low Latency and Active Evaluation

23:34 Synthetic Data and Ground Truth

25:07 Interoperable Agent Schema