NEWS · MODELS · #272
Integrating DMN Decision Models, LLMs and NeMo to Produce Auditable Agentic Architectures
Alex Porcelli outlines a response to a key enterprise AI problem—non-deterministic outputs and lack of accountability—by describing how combining DMN decision models with LLMs, agent skills and NeMo guardrails can yield auditable, deterministic agentic architectures that let business leaders own decision logic while engineers retain architectural governance.
KEY POINTS
- Alex Porcelli outlines a response to a key enterprise AI problem—non-deterministic outputs and lack of accountability—by describing how combining DMN decision models with LLMs, agent skills and NeMo guardrails can yield auditable, deterministic agentic architectures that let business leaders own decision logic while engineers retain architectural governance.
- This matters because combining formal decision models with LLMs and guardrails can increase determinism and accountability in high‑stakes enterprise AI decisions, improving governance and risk management.
- Presentation: Decision Models in Agentic Architectures: From Production to Agent Skills
WHY IT MATTERS
This matters because combining formal decision models with LLMs and guardrails can increase determinism and accountability in high‑stakes enterprise AI decisions, improving governance and risk management.