Programming with an AI Agent
Artificial intelligence (AI) has fundamentally changed the way we program. AI agents can generate code, optimize it, and even help with debugging. However, there are some limitations that programmers need to keep in mind when working with AI.
Issues with ordering and duplication
AI agents struggle with the correct order of code. For example, they may place initializations at the end of a file, causing runtime errors. Additionally, AI can readily 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 is to use 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 may 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 can invoke the large language model. These tools are based on an open standard protocol (MCP). It is therefore possible to connect an AI coding agent to an IDE such as Visual Code. You can optionally set up a local LLM with llama or Ollama and choose an MCP server to integrate with. NetCare has a MCP server created to help with debugging and managing the underlying (Linux) system. Handy for when you want to deploy the code live directly.
Models can be found at 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 detect and correct errors early. They provide 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 AI agents keep repeating mistakes lies in how they interpret AI APIs. AI models need context and a clear role description to generate effective code. This means prompts must be complete: they should not only contain functional requirements but also explicitly specify the expected outcome and constraints. To facilitate this, you can store prompts in a standard format (MDC) and always send them to the AI. This is especially useful for generic programming rules you follow, 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 provide solutions to make AI handle context better. FAISS, for example, helps with efficient searching and retrieving of relevant code snippets, while LangChain assists in structuring AI‑generated code and maintaining context within a larger project. You can also set this 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.
Take contact to help set up the development environment so teams can get the most out of it and spend more time on requirements engineering and design rather than debugging and coding.
