Deterministic Steps versus LLM Steps
By the end of this module you can decide which nodes need a language model and which are ordinary functions, and stop paying for judgement where logic will do.
Units
- Unit 03.00: Which decisions need judgement
- Unit 03.01: Paying a model to do arithmetic
- Unit 03.02: Making an LLM step's output checkable
- Unit 03.03: Falling back to code when the model is unsure
- Unit 03.04: The cost difference over a thousand runs
