Stage 1 · Lesson 2 of 6
Workflows versus agents
In a , you decide the steps in code and the model fills in parts of a fixed path, such as summarise, then classify, then draft a reply. In an , the model chooses what happens next based on what it has seen. Workflows are cheaper, faster, easier to test and easier to explain to a manager.
Agents are worth their extra cost only when the path genuinely cannot be written down in advance, for example when a support ticket might need an order lookup, a refund, a replacement or a human, in any order. Many successful 'agent' products are mostly workflows with one agentic step. Learn to sketch both designs for the same problem before writing code.
Common trapbuilding an agent because it sounds impressive, when a three-step workflow would do the job more reliably and at a tenth of the cost.
A question to check yourself, an AI practice session and 1 cheat sheet entry come with the full roadmap. Unlock
Resources for this stage
Start with· follow one of these
- CoursePaidGrokking Modern AI Fundamentals
Design Gurus · Beginner · $72 one-time
Chapter 8, Agentic AI, covers reasoning, planning and memory in agents and ends with a small agent project
- CourseFreeHugging Face AI Agents Course
Hugging Face · Beginner
Free: Unit 1 explains the thought, action, observation cycle and builds a first agent step by step