Agentic Engineering
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 will challenge your understanding.
Ai délégation goes from assistance to self driving.
Choose mode depending on risk, expertise
Tips
In this topic
- 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…
- Levels of agentic programmingGrowingfurther reading
Use AI for code reviews when the risk is low.
- Agent friendly codebaseSeedlingfurther reading
- LLM as JudgeSeedlingfurther reading
- Agent routingGrowingfurther reading
One way to do AI Multi Agent could be to route the request to the right model depending on the complexity needed, at least to save costs. https://blog.bytebytego.com/p/how-smart-model-routing-can-cut-llm.
- AI - Single agent vs multi agentGrowingfurther reading
Frontier models are good by themselves (ie Claude Code) Single agent (could) need more human in the loop to review, where multi agent could review itself.
- AI Multi AgentEstablishedfurther reading
They have an architect, scout, coder, reviewer and verifier. https://github.com/jarod-rosenthal/workermill. They have a planner, a developer (frontend, backend, devops), a tech lead. The tech lead reviews the code. Up to 3 times.
- How to best use AI in engineeringGrowingfurther reading
Treat AI as a slow and non-deterministic (AI outcome is not deterministic) worker that can get things wrong, don't use it for critical paths like auth. A good chef that delegates is…
- LangchainSeedlingfurther reading
useful for production apps that leverage llms beyond calling openai/claude with an api and show the results. this is useful if you need things like subagents doing different things (searching, etc.), orchestration,…
- RAG - Retrieval-Augmented GenerationGrowingfurther reading
A model has to: find every one of those. realise they're related. ignore 99% of everything else. remember them all. compare them. That's basically Retrieval-Augmented Generation (RAG), except your retrieval system is…
Continue with →
- Agent friendly codebaseSeedlingfurther reading
- Levels of agentic programmingGrowingfurther reading
Use AI for code reviews when the risk is low.
- Agent routingGrowingfurther reading
One way to do AI Multi Agent could be to route the request to the right model depending on the complexity needed, at least to save costs. https://blog.bytebytego.com/p/how-smart-model-routing-can-cut-llm.