{"slug": "ask-hk-how-are-you-building-ai-apps-today", "title": "Ask HK: How are you building AI apps today?", "summary": "Developers are increasingly integrating large language model APIs into custom applications, moving beyond standard tools like Cursor and Windsurf. Many are building bespoke architectures that directly interface with the APIs to create unique functionalities. This trend highlights a shift toward more tailored AI solutions as the technology matures.", "body_md": "| ||||||||||||||||\n3 points by |\nGenerally curious how folks are using LLM APIs today. Are folks doing anything bespoke, unique or different? I think we've seen a lot of usage with harnesses, CLIs, Cursor/Windsurf etc which uses the APIs underneath. If you are using the API itself, what does your architecture look like with said API?\n| |||||||||||||||\n|", "url": "https://wpnews.pro/news/ask-hk-how-are-you-building-ai-apps-today", "canonical_source": "https://news.ycombinator.com/item?id=48323554", "published_at": "2026-05-29 14:30:19+00:00", "updated_at": "2026-05-29 14:46:04.722660+00:00", "lang": "en", "topics": ["large-language-models", "artificial-intelligence", "ai-tools", "ai-products", "ai-infrastructure"], "entities": ["Cursor", "Windsurf"], "alternates": {"html": "https://wpnews.pro/news/ask-hk-how-are-you-building-ai-apps-today", "markdown": "https://wpnews.pro/news/ask-hk-how-are-you-building-ai-apps-today.md", "text": "https://wpnews.pro/news/ask-hk-how-are-you-building-ai-apps-today.txt", "jsonld": "https://wpnews.pro/news/ask-hk-how-are-you-building-ai-apps-today.jsonld"}}