Agentic Mesh

Chapter 13. Trust Framework and Governance

A note for Early Release readers

With Early Release ebooks, you get books in their earliest form—the author’s raw and unedited content as they write—so you can take advantage of these technologies long before the official release of these titles.

This will be the 13th chapter of the final book. The GitHub repo will be made active later on.

If you’d like to be actively involved in reviewing and commenting on this draft, please reach out to the editor at [e-mail].

Industry observers say that agents will streamline business processes, transform jobs, and usher in a new era of innovation. At least, that is the promise. However, one thing is certain about new technologies: even if they are inexpensive, and even if they are incredibly powerful, unless they are trusted they will not be used and will never achieve widespread adoption. The same goes for agents. Unless we trust them – and given their potential impact, unless we really trust them - adoption will stall.

Simply put: we – individuals and organizations – will not use agents that we do not trust.

So, trust is crucial, but what does it mean to trust an agent? In simple terms, we trust an agent if they do what they are supposed to do—if they adhere to their original purpose and policies that are guardrails for its behavior. How do we certify that an agent is doing what it is supposed to do? How do we capture the relevant metrics and information to begin to support a certification ...