Collected sources and patterns will appear here. Add from search, explore, or the patterns library.
Payload -> LLMResponse
Dispatch execution payloads (e.g., extraction, querying) to specialized LLM configurations optimized for those distinct functional roles.
Problem it solves
Using a single generic LLM model configuration for all agentic tasks leads to suboptimal quality or high cost.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.