| ▲ | gavinray 3 hours ago | ||||||||||||||||
It's really cool to see that other people run into the same issues and arrive at the same conclusions/solution. At $DAYJOB, we have an LLM-based tool and this issue of "how do we avoid burning tokens solving the same problems over again" was an early obstacle We wound up building a very similar thing to what you call "tools" (we named them "Saved Programs"). There's a wiki the LLM searches before solving a problem, that links saved programs for past actions to their content entry. If it finds one, it'll re-use it, otherwise it'll generate a program and offer to save it, if you think it'll be common enough. | |||||||||||||||||
| ▲ | afshinmeh 3 hours ago | parent | next [-] | ||||||||||||||||
> how do we avoid burning tokens solving the same problems over again Letting the LLM write half baked tools is the recipe for burning more tokens. > There's a wiki the LLM searches before solving a problem, that links saved programs for past actions to their content entry. What's the criteria for marking an LLM written tool as useful/correct before publishing it? | |||||||||||||||||
| |||||||||||||||||
| ▲ | Edmond 3 hours ago | parent | prev [-] | ||||||||||||||||
it's called workflow automation: https://blog.codesolvent.com/2025/12/workflow-automation-let... Everyone is just taking a round about way to get there. The workflow/program as "tools" approach is the right one. Agents skills are more or less in that same direction. | |||||||||||||||||