Our team uses Acme Tech to power several AI-based support and automation workflows, and we would like the ability to choose which language model is used for each use case. Right now, we can use the platform for our AI tasks, but we need more flexibility to select a specific model based on cost, speed, or accuracy requirements. For example, we may want to use a faster, lower-cost model for simple questions and a more advanced model for complex technical requests. Having custom LLM selection would help us better control performance, manage budgets, and tailor the experience for different types of users.
Our team uses Acme Tech to power several AI-based support and automation workflows, and we would like the ability to choose which language model is used for each use case. Right now, we can use the platform for our AI tasks, but we need more flexibility to select a specific model based on cost, speed, or accuracy requirements. For example, we may want to use a faster, lower-cost model for simple questions and a more advanced model for complex technical requests. Having custom LLM selection would help us better control performance, manage budgets, and tailor the experience for different types of users.