I'm growing more and more frustrated at engineers wasting time building AI tools. I'm seeing a lot of people building these tools but not actually making anything. Documentation, memory, skills/plugins... I just don't think a lot of these actually DO anything and most people's time would be better spent using the LLMs to build software for people. Not more software for LLMs.
Anybody else noticing this? Anybody else hacking away all the bespoke tools, complex markdown files, and other extra stuff and just relying on the frontier models (and maybe an mcp or two to get your LLM controlled access to specific resouces)?