OpenAI Codex Made Crystal Clear · chapter 2: One Agent, Four Surfaces

The surface decision map

2026-09-12

The branch labels are the community's own questions. The left two lanes are pairing (you watch and steer), the right two are delegation (the agent works, you review the result). Come back to this map after chapter 7, when the right half will be muscle memory.

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.

Now the decision itself. Community threads agonize over "CLI or app?" and "IDE or cloud?" as if it were an identity choice. It is a per-task choice, and it takes about five seconds once you ask the right question: how much do you need to watch this work happen? Figure 2.2 turns that into the decision map, with the branches phrased the way readers actually ask them.

Figure 2.2: The surface decision map. The branch labels are the community's own questions. The left two lanes are pairing (you watch and steer), the right two are delegation (the agent works, you review the result). Come back to this map after chapter 7, when the right half will be muscle memory.
Figure 2.2: The surface decision map. The branch labels are the community's own questions. The left two lanes are pairing (you watch and steer), the right two are delegation (the agent works, you review the result). Come back to this map after chapter 7, when the right half will be muscle memory.

Recap

  • The idea: The branch labels are the community's own questions.
  • The picture: Figure 2.2, from chapter 2 ("One Agent, Four Surfaces") of OpenAI Codex 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 OpenAI Codex Made Crystal Clear.

Every chapter opens with the gist, draws the hard ideas, and ends with recipes and sources.

Get the book

All diagrams