"Now that we've compressed nearly all human knowledge into large language models, the next frontier is tool calling. Chaining together different AI tools enables automation. The shift from thinking to doing represents the real breakthrough in AI utility. I've built more than 100 tools for myself, & they work most of the time, but not all the time. I'm not alone. Anthropic's Economic Index report reveals that 77% of business use of Claude centers on full-task automation, not co-piloting."
"The guidance was counterintuitive : instead of many simple tools with clear labels, create fewer, more complex tools. Here are the seven email tools I built - Ruby scripts, each with a clear purpose. The "Safe Send Email" script was designed to prevent the AI from sending emails without approval. Beautifully naive, simple, & clear, Shouldn't a language model be able to read these & know exactly what I was asking it to do? But it's not this simple!"
Large language models have centralized human knowledge, and the next phase is tool calling to chain AI tools for full-task automation. Many personal tools were built but often fail; 77% of business use targets full-task automation rather than co-piloting. Anthropic's guidance recommends fewer, more complex, parameter-rich tools to improve token efficiency, with research showing average output-token savings. Consolidating simple tools into unified, comprehensive tools yields near-100% success rates, faster responses, and substantial token savings. CRM, calendar, and database workflows become more reliable and less costly when redesigned for AI cognition instead of human intuition.
Read at Tomasz Tunguz
Unable to calculate read time
Collection
[
|
...
]