AI Agents Made Crystal Clear · chapter 2: What an Agent Actually Is
The same job, two architectures
2026-09-04
On the left every arrow is something a developer typed. On the right the arrows are dashed because they do not exist until the run happens: the model picks a tool, sees the result, and picks again. That single difference sets the cost, the latency, the failure modes and how you debug it.
Below: the paragraph from the book that builds this idea, then the diagram itself (Figure 2.2), and a recap. About a minute of reading.
Strip both sentences down and one word does the work: predefined. In a workflow the path exists before the run starts, in your source code, where you can read it, diff it and test it. In an agent the path comes into existence during the run, one decision at a time. Figure 2.2 puts the two side by side.
Recap
- The idea: On the left every arrow is something a developer typed.
- The picture: Figure 2.2, from chapter 2 ("What an Agent Actually Is") of AI Agents Made Crystal Clear.
- Go deeper: the chapter builds this step by step, with recipes and sources at the end.
This diagram is one of many in AI Agents Made Crystal Clear.
Every chapter opens with the gist, draws the hard ideas, and ends with recipes and sources.
Get the book
