Presentation: Decision Models in Agentic Architectures: From Production to Agent Skills
Computer ScienceInformation Systems
THE AI ANGLE
Managing ambiguous, conversational data intake within an agentic architectureAlex Porcelli outlines the enterprise challenge of non-deterministic outputs and missing accountability when applying AI to high-stakes, regulated decisions. He demonstrates how integrating deterministic DMN decision models with LLMs, agent skills, and NeMo guardrails creates auditable agentic architectures. This architecture illustrates to instructors how modern enterprise systems must balance flexible generative interactions with rigorous architectural governance and rule-based compliance.
THE TEACHING ANGLE
Students can evaluate the architectural trade-offs between deploying non-deterministic LLM agents and enforcing deterministic, auditable decision rules in regulated enterprise settings.Read the original at infoq.com Generate teaching or study materials
More in Computer Science
- Early Anthropic hire, former METR COO have found a way to rein in rogue AI agentsTechCrunch · September 15, 2026
- AI’s best coding agent fails 60% of the time — and the data backs it upThe New Stack · September 15, 2026
- The ERP reckoning: Decades of customization could block AI valueCIO.com · September 15, 2026
- Open weights are not open source: Why AI's favorite label is under disputeThe Register · September 15, 2026
- Exclusive: Paying for frontier AI models buys 4-month head start at 5x the costArs Technica · September 15, 2026