Since I made the placeholder website there have been remarkable advances in artificial intelligence (ChatGPT and its cousins). In particular they have become very good at writing software (if guided carefully!). In September 2025 I decided to explore whether an AI engine could be useful in moving the placeholder website to a stable, full-featured site.<\/p>\n\n\n\n
I asked Claude. The results I think are remarkable. You can reach your own conclusions.<\/p>\n\n\n\n
Later, I asked Claude to describe itself and it gave this rather self-serving answer:<\/em><\/p>\n\n\n\n In an hour of conversation between Claude and me, Claude had looked at the content of this placeholder website and understood it. Together we explored ways in which Claude could be asked to do the heavy-lifting for the task of creating a real website. The outcome is a series of documents for “us” to review – listed below. The reviewed documents, with our changes, can be offered back to Claude, and the hope is that Claude would then use those documents to create the real website. There are some tasks which require a human to do manually, and this is described in the “Development Workflow” document.<\/p>\n\n\n\n <\/p>\n\n\n\n These documents were created (with the exception of this one!) by Claude on 18 September 2025. Our conversation<\/a> is saved and can be read (not necessary, but you might be interested in the process). My first two questions were generic questions, relating to how Claude might work to make a database accessible to smartphone apps. From my third question onward the topic was specific to the Grow Native project.<\/p>\n\n\n\n Claude created 6 documents (listed below). I then asked for another one that summarised these and next steps. This is Project Documents Overview<\/a>.<\/p>\n\n\n\n I’ve created a comprehensive set of markdown documents that will guide your GrowNative NZ project implementation:<\/p>\n\n\n\n Since I made the placeholder website there have been remarkable advances in artificial intelligence (ChatGPT and its cousins). In particular they have become very good at writing software (if guided carefully!). In September 2025 I decided to explore whether an …<\/p>\nClaude is an AI assistant created by Anthropic, designed to be helpful, harmless, and honest in conversations and tasks. Like ChatGPT (made by OpenAI), Claude is a large language model that can assist with writing, analysis, coding, and answering questions, but with Anthropic's focus on AI safety and responsible development. You can try Claude at https:\/\/claude.ai<\/a>.<\/code><\/p>\n\n\n\nClaude Conversation<\/h2>\n\n\n\n
Document Overview<\/h2>\n\n\n\n
Claude’s Documents<\/h2>\n\n\n\n
\n