crux-skill-memory-meditation-ensemble

Cross-model synthesis compares independent AI research outputs to identify convergent findings, divergent conclusions, and unique insights while tracking provenance. It aggregates multiple model consolidations into a unified analysis report with evidence comparisons and citations.

To aggregate multiple AI research trees, orchestrate consolidation files and finalisation YAML data through user decision gates. The ensemble meditation workflow compares findings, manages enhancement candidates, and routes accepted improvements to generate a final synthesis report.

Ensemble meditation workflows require completed meditation trees, consolidation files, and finalisation YAML data as inputs. These prerequisites enable the cross-model aggregation, enhancement selection, and ensemble report handoff procedures.

The best way to track provenance and disagreements is using ensemble synthesis to compare multiple model consolidations. This preserves model attribution, identifies divergent conclusions, and highlights high-value discoveries within a unified cross-model analysis.

Yes, you can manage user decision gates during cross-model aggregation. The workflow aggregates per-tree enhancement candidates, performs cross-model reflection, presents decision gates to the user, and routes accepted improvements automatically.

You should not use ensemble meditation workflows when your research involves a single AI model tree rather than multiple independent outputs. The workflow requires multiple model consolidations to perform cross-model comparison, convergence tracking, and divergence analysis.