Model-agnostic architecture
A model-agnostic architecture treats the large language model as a configuration field rather than an architectural commitment: which model an agent uses is declared per agent, and switching providers is a configure-and-re-evaluate operation, not a re-architecture. It protects against provider lock-in and lets quality, cost and residency drive model choice.
In NeoXam Agents
The model is a field in each agent's descriptor. Shipped agents run on Anthropic Claude via an AI gateway today; changing models is a configuration change re-validated by the eval gate. No model is ever fine-tuned on client data, so nothing holds a client to any provider.
Related terms
See how these concepts come together in a governed agentic platform for investment operations.
Explore the platform