Search papers, labs, and topics across Lattice.
This paper introduces progressive crystallization, a novel lifecycle approach that transforms AI agent exploration into a more efficient, deterministic workflow for IT operations. By implementing a three-stage execution taxonomy and an evidence-based promotion mechanism, the authors achieved a significant increase in deterministic execution from 0% to 45% over eight months, while simultaneously reducing per-incident costs by over 70% despite a doubling in incident volume. The findings underscore the potential for AI agents to transition from costly, continuous inference models to more sustainable and reproducible workflows, enhancing both economic efficiency and operational safety.
Transforming AI agent exploration into a deterministic workflow can slash operational costs by over 70% while doubling incident handling capacity.
AI agents deployed for IT operations are typically permanent cost centers because every execution requires full LLM inference, even for previously solved problems. This paper introduces progressive crystallization, a lifecycle that treats agent exploration as a discovery mechanism rather than a permanent execution model. It defines a three-stage execution taxonomy, from fully agent-orchestrated to hybrid to fully deterministic workflows, together with an evidence-based promotion mechanism that converts repeatedly validated agent behaviors into cheaper and more reproducible deterministic workflows, while automatically demoting workflows that regress. Evaluated on a production cloud networking AIOps system processing tens of thousands of incidents per month, the approach increased deterministic execution from 0% to 45% over eight months, reduced per-incident agent costs by more than 70% despite doubling incident volume, and improved safety through greater reproducibility and auditability. The paper also presents the execution taxonomy, promotion and demotion criteria, trace extraction methodology, economic model, safety considerations, and discusses limitations and threats to validity.
