Glossary
LLM orchestration
In short
Coordinating one or more large language models, and the steps around them, to complete a task that a single prompt would not handle well on its own.
A single call to one model is enough for simple work. Harder tasks need structure: send the prompt to several models, compare or merge their answers, retry on failure, pause for a human, or chain one step into the next. Arranging all of that is orchestration.
You can do it in code with a framework, or run it on a platform that handles the coordination for you. The hard parts are usually not the model calls themselves but everything around them: state, retries, cost tracking, and combining outputs sensibly.
In LLMWeave
LLMWeave is orchestration as a managed product. You set up a weave, and the platform handles fanning your task out across models, synthesizing the results, and running the whole thing durably, without you writing or operating the orchestration layer.
Related terms
Multi-model AI
Using more than one AI model on the same task, instead of relying on a single model for every answer.
Response synthesis
Merging several model answers into one clean result, rather than showing them side by side and making you pick.
Model routing
Sending each task, or each part of a task, to the model best suited for it, rather than using one model for everything.
Try multi-model on your task
One prompt, several models, one answer. Free to start, no card.
Get started