Collected sources and patterns will appear here. Add from search or the patterns library.
TaskRequirements -> LLMModelConfig
Route a subtask to the most cost-effective LLM provider/model that meets or exceeds the minimum required task capability threshold.
Problem it solves
Directing every agent-driven tool call to premium frontier models causes unsustainable API costs.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.