Hey there! I’ve been working on DB Pilot for the last couple of months, and I recently added an AI assistant powered by GPT 3.5 to help you write SQL queries tailored to your DB schema.Simply ask what data you are looking for - GPT will figure out which tables to use, how to join them, and then write a query for you.The AI assistant knows which tables and columns exist in your database, meaning it can write queries specific to your schema.Besides that, it doesn't have access to any actual data from your database though, meaning your data doesn't get exposed to OpenAI.
Users are inquiring about admin panel location, MongoDB support, and SQLite. They discuss the need for SQL knowledge to use AI effectively, and suggest improvements like API/SDK integration and database structure recommendations. Concerns include AI's incorrect code, security of common API keys, and handling ChatGPT's token limit. Positive feedback mentions AI's time-saving capabilities and assistance in coding practices. There's interest in Windows support, Linux usage, and integration into apps. Typos on the homepage and issues with Supabase Postgres DB were noted. Questions about the use of Rust and alternative AI models like LLama or BERT were also raised.
Users criticized the Show HN product for an unclear admin panel location, ambiguous pricing, and a lack of clarity in AI responses. Concerns were raised about the AI providing incorrect code, requiring prior knowledge, and being less efficient than manual coding. The product's support for databases and operating systems was deemed insufficient, with no SQLite or Windows support and missing Linux instructions. Security concerns were mentioned regarding common API keys and public personal data. Users also noted typos, a lack of one-time payment visibility, and the absence of a recommendation feature for database changes.