AI agent
An AI agent is a software capability that uses a large language model to perform a bounded task — investigating, drafting, validating — by reasoning over context and calling tools. In a governed enterprise platform, an agent is declared and versioned: its prompt, model, tools and input/output schemas are defined in a reviewed descriptor, making its behavior auditable.
In NeoXam Agents
Every agent is declared in a Git-governed catalog — 'no agent without a descriptor' — and invoked by NeoXam products exactly where reasoning is needed: the application decides what and when; the agent decides how, within a bounded task. Agents run in task or conversational mode, return schema-validated outputs, and never orchestrate business workflows.
Related terms
See it at work
Reconciliation break investigation
Shipped — V0 pilotOne click on a break: the agent investigates match history and pricing, then returns root cause, evidence and a recommended action — fully traced.
See how these concepts come together in a governed agentic platform for investment operations.
Explore the platform