Levels of agentic programming
Inspired by How much can you delegate to agents?
Use AI for code reviews when the risk is low.
Continue with →
- AI Loop EngineeringGrowingfurther reading
Smolagents vs langgraph. To test the output of your models, you can rely on both deterministic and non-deterministic guardrails (LLM as Judge). Remember that AI outcome is not deterministic so it's safer…
← Comes after
- Agentic EngineeringGrowingfurther reading
Reviewing code is a skill that won't go away. No shortcut to it, get good the old school way. Take the time to write the project description and code structure yourself, it…
Sources
- How much can you delegate to agents? inspired this note
- Agentic Autonomy Levels cited