Workflow vs agent
Who decides the next step: your code or the model.
What you’ll learn
Four ideas, one module
The agent loop
Observe, decide, act, update state. Repeat until done or stopped.
Errors compound
Why a chain of mostly good steps can still fail as a whole.
Autonomy by design
Where a human approves, and when a plain workflow is the better choice.
Applied exercise
Redesign four use cases
Redesign four use cases as workflows, partially agentic systems and autonomous agents, then compare risk.
- Customer refund requests
- Weekly sales report
- Competitor research brief
- Night-time incident response
Cheat sheet
Autonomy is a cost: give the model a decision only where code can’t cover the cases
One page you keep: the questions to ask on every project, the rules of thumb, and a decision guide you can use on your own product. All ten come with The Book.
Leave at the door
Five myths this module breaks
| Myth | What’s actually true |
|---|---|
| “More agentic is always better.” | More autonomy adds variance, cost and risk too. |
| “The agent takes the action.” | The model requests it. Your system executes it. |
| “It made a plan, so it stays on track.” | A plan is text. Only checks keep it on track. |
| “More agents give better answers.” | Each hand-off adds cost and a chance to fail. |
| “A human in the loop makes it safe.” | Only if they see the evidence and can say no. |
Before you move on
Can you call this one?
A research agent misreads a figure at step 2. The report builds on it.
Why did the error spread? Name two design changes that would have caught it earlier.
How we would answer
- Why it spread later steps treat earlier results in state as facts. Nothing re-checked the figure, so every step built on it.
- Check observations compare the extracted figure against the source before storing it.
- Add a checkpoint a code check or human review before key numbers are used downstream.
- Require citations for every figure, and verify them automatically.
- Make the known steps a fixed workflow, so fewer steps are left to the model.
- Not enough on its own a bigger model. It lowers the per-step error but doesn’t stop propagation.
Every module ends on a question like this. Join the waitlist →
The Autonomy Engineer
Cleo Maren
builds and breaks agent workflows to discover when independent AI becomes useful and when it becomes chaos.
Episode 08 · Agents without the mythology
Included with the course.
Coming soon · an AI character from the show, not a real researcher.
Next · Module 09