Presentation: Decision Models in Agentic Architectures: From Production to Agent Skills

7.4 relevance

Decision models in agentic architectures, directly relevant to AI agent orchestration.

AI/ML infoq.com

Answer the board on AI readiness

Arrive with evidence, not opinion. See how your foundation benchmarks against your peers, get a clear read, and leave with a ranked place to start.

Why It Matters

For platform and AI engineers building agentic systems, Porcelli's DMN+LLM pattern provides a pragmatic path to auditability and determinism—solving the core accountability gap that prevents enterprise adoption of AI agents in regulated or high-stakes workflows.

Key Takeaways

Adopt DMN decision models as the deterministic backbone for agent skills, decoupling business logic from LLM inference while maintaining full audit trails through guardrail integration.

Presentation: Decision Models in Agentic Architectures: From Production to Agent Skills

Summary

Alex Porcelli of Aletyx addresses the enterprise AI challenge of non-deterministic outputs by integrating DMN (Decision Model and Notation) decision models with LLMs, agent skills, and NeMo guardrails to create auditable, deterministic agentic architectures. His approach separates business-owned decision logic from engineering-managed architectural governance, enabling consistent, repeatable answers to identical queries—a critical requirement for high-stakes production environments. Porcelli draws on 20+ years of experience with Drools, jBPM, and Kogito to bridge deterministic reasoning with generative AI.

Author

Alex Porcelli