When given ambiguous instructions, LLMs will choose the most common technology stack from their training data (e.g., React with Tailwind), even if it contradicts the project's goals. Developers must provide explicit constraints to avoid this unwanted default behavior.
Related Insights
AI development tools can be "resistant," ignoring change requests. A powerful technique is to prompt the AI to consider multiple options and ask for your choice before building. This prevents it from making incorrect unilateral decisions, such as applying a navigation change to the entire site by mistake.
The top 1% of AI companies making significant revenue don't rely on popular frameworks like Langchain. They gain more control and performance by using small, direct LLM calls for specific application parts. This avoids the black-box abstractions of frameworks, which are more common among the other 99% of builders.
When asked to modify or rewrite functionality, LLMs often attempt to preserve compatibility with previous versions, even on greenfield projects. This defensive behavior can lead to overly complex code and technical debt. Developers must explicitly state that backward compatibility is not a requirement.
Atlassian improved AI accuracy by instructing it to first think in a familiar framework like Tailwind CSS, then providing a translation map to their proprietary design system components. This bridges the gap between the AI's training data and the company's unique UI language, reducing component hallucinations.
To get precise results from AI coding tools, use established design and development language. Prompting for a "multi-select" for dietary restrictions is far more effective than vaguely asking to "add preferences," as it dictates the specific UI component to be built and avoids ambiguity.
To enable AI agents to effectively modify your front-end, you must first remove global CSS files. These create hidden dependencies that make simple changes risky. Adopting a utility-first framework like Tailwind CSS allows for localized, component-level styling, making it vastly easier for AI to understand context and implement changes safely.
When using AI for complex but solved problems (like user permissions), don't jump straight to code generation. First, use the AI as a research assistant to find the established architectural patterns used by major companies. This ensures you're building on a proven foundation rather than a novel, flawed solution.
LLMs may use available packages in a project's environment without properly declaring them in configuration files like `package.json`. This leads to fragile builds that work locally but break on fresh installations. Developers must manually verify and instruct the LLM to add all required dependencies.
To avoid generic, 'purple AI slop' UIs, create a custom design system for your AI tool. Use 'reverse prompting': feed an LLM like ChatGPT screenshots of a target app (e.g., Uber) and ask it to extrapolate the foundational design system (colors, typography). Use this output as a custom instruction.
Lovable is a solid AI tool for rapid prototyping, but its reliance on default UI libraries like Tailwind CSS results in products that all share a similar aesthetic. This lack of visual diversity is a significant drawback for creating a unique brand identity or user experience.
