In this chapter, we pull together the patterns from the first nine chapters into an application that demonstrates how patterns interact with one another to enable you to build production-ready agentic applications that get better over time.
The full code for this chapter can be found in the GitHub repository of this book. Please open the code in your favorite Python IDE and follow along with us.
Agentic Workflow
Rather than build out a full application in this chapter, we’ll demonstrate a vertical slice of an application that corresponds to a customer use case. In GenAI, vertical slices like this often correspond to a user-driven (manual) workflow that is in the process of becoming AI assisted or fully automated. AI assistants are called copilots, and autonomous AI are termed agents. Any application on this spectrum is termed agentic. Thus, what we are demonstrating in the GitHub repository is an agentic workflow.
The workflow is intended to create educational content; this is the same use case we explored in the description of Pattern 23, Multiagent Collaboration. It is depicted in Figure 10-1. Note that unlike in Figure 7-5, there are two stages of review (instead of just one) and the data being transferred is depicted. Also, there are a few more writers in the content-writing team, including one who will write on GenAI topics based on the content of this book.
Figure 10-1. Collaboration among agents in the end-to-end example of creating ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month, and much more.
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.
Julian F.
Head of Cybersecurity
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.
Addison B.
Field Engineer
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.
Amir M.
Data Platform Tech Lead
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.
