How I rebuilt my AI chatbot without RAG: bigger context windows, prompt caching and tool-using agents replaced embeddings and a vector database.

While AI tools can generate complex code quickly, they don't eliminate the need for technical knowledge. The piece argues that AI is better used as a learning tool to develop foundational technical understanding rather than as a replacement for coding skills.

How I built ZeidBot - a RAG chatbot using Vector DBs, LLMs, embedders and LangChain. Using tools within the AI-stack and building reasoning applications with precision and control.

Step-by-step walkthrough showing how to harness the power of AI locally. Learn to run language models on your own computer, opening up new possibilities for privacy-focused and tailored AI applications.

The most important thing for a startup is to get the MVP validated as quickly as possible. Use off the shelf products to quickly build the undifferentiated features of your product and focus your resources on what makes you unique.

Web applications combine layers—like frontend (HTML, CSS, JS), backend (Node, Python), databases, and infrastructure—which are "stacked" to form a web application.

As a frontend engineer learning CSS properly will save you time and your sanity in the long run irrespective of which styling approach you use.