Programming with an AI Agent
Artificial intelligence (AI) has fundamentally changed the way we program. AI agents can generate code, optimize it, and even assist with debugging. However, there are some limitations that programmers must keep in mind when working with AI.
Problems with sequence and duplication
AI agents struggle with the correct ordering of code. For example, they might place initializations at the end of a file, which causes runtime errors. Furthermore, AI can unhesitatingly define multiple versions of the same class or function within a project, leading to conflicts and confusion.
A code platform with memory and project structure helps
One solution for this is using AI code 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 might lose the coherence of a project and introduce unwanted duplications 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 possible to link an AI coding agent to an IDE such as Visual Code. Optionally, you can set up an LLM locally with llama of Ollama and you choose an MCP server to integrate with. NetCare has created a MCP server to help with debugging and managing the underlying (Linux) system. Useful for when you want to deploy the code live immediately.
Models can be found on huggingface.
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 to detect and correct errors early on. They form an essential complement to AI-generated code to ensure quality and stability.
The cause of recurring errors: context and role in APIs
One of the main reasons why AI agents continue to repeat errors lies in how AI interprets APIs. AI models require context and a clear role description 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 boundary conditions. To facilitate this, you can store the prompts in a standard format (MDC) and send them to the AI by default. This is especially useful for generic programming rules you adhere to, 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 to help AI better handle context. FAISS, for example, assists in efficiently searching and retrieving relevant code snippets, while LangChain helps in structuring AI-generated code and maintaining context within a larger project. However, you can also potentially set this up locally yourself using vector 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 which still requires guidance and correction to achieve a good result.
Contact touch up to help set up the development environment to assist teams in getting the most out of the development environment and spending more time on requirements engineering and design than on debugging and writing code.
