Programming with an AI Agent
Artificial intelligence (AI) has fundamentally changed the way we program. AI agents can generate and optimize code and even help with debugging. However, there are several limitations that programmers need to keep in mind when working with AI.
Problems with sequencing and duplication
AI agents struggle with placing code in the correct order. For example, they may place initializations at the end of a file, causing runtime errors. In addition, AI may define multiple versions of the same class or function within a project without hesitation, leading to conflicts and confusion.
A coding platform with memory and project structure helps
One solution is to use AI coding platforms that can manage memory and project structures. This helps maintain consistency in complex projects. Unfortunately, these features are not always applied consistently. As a result, the AI may lose track of a project's coherence and introduce unwanted duplicates or incorrect dependencies during programming.
Most AI coding platforms work with so-called tools that the large language model can invoke. These tools are based on an open standard protocol (MCP). It is therefore also possible to connect an AI coding agent to an IDE such as Visual Code. Alternatively, you can set up an LLM locally with Llama or Ollama and choose an MCP server to integrate with. NetCare has created a MCP server to help with debugging and managing the underlying (Linux) system. This is useful if you want to deploy the code live immediately.
Models can be found on Hugging Face.
IDE extensions are indispensable
To better manage AI-generated code, developers can use IDE extensions that monitor code correctness. Tools such as linters, type checkers, and advanced code analysis tools help detect and correct errors at an early stage. They are an essential complement to AI-generated code for ensuring quality and stability.
The cause of recurring errors: context and roles in APIs
One of the main reasons AI agents keep repeating mistakes lies in the way AI interprets APIs. AI models need context and a clear role definition to generate effective code. This means that prompts must be complete: they should not only contain the functional requirements, but also explicitly state the expected result and the constraints. To make this easier, you can save prompts in a standard format (MDC) and automatically include them with the AI. This is particularly useful for the generic programming rules you apply, as well as the functional and technical requirements and the structure of your project.
Tools such as FAISS and LangChain help
Products such as FAISS and LangChain offer solutions for helping AI work better with context. For example, FAISS helps search for and retrieve relevant code snippets efficiently, while LangChain helps structure AI-generated code and maintain context within a larger project. Here too, you can optionally set it up locally yourself using RAC databases.
Conclusion: useful, but not yet independent
AI is a powerful tool for programmers and can help accelerate development processes. However, it is not yet truly capable of independently designing and building a more complex codebase without human oversight. Programmers should view AI as an assistant that can automate tasks and generate ideas, but that still requires guidance and correction to achieve a good result.
Get in contact to help set up the development environment, enabling teams to get the most out of it and focus more on requirements engineering and design rather than debugging and writing code.
