consolidate-research

To synthesize research from multiple AI models, provide your research outputs alongside a consolidation manifest. The tool reconciles findings from different sources into a single, provenance-enriched report with quality metrics.

Provenance tracking in research synthesis tags findings with their original sources. It uses a pattern registry to drive provenance tagging, quality scoring, and cross-model reconciliation so you know exactly where each consolidated finding originated.

Yes, you can synthesize research findings without a manifest using standalone operation. While manifest-driven mode aligns with upstream guidance, standalone mode supports ad-hoc research synthesis by providing just your research outputs.

Yes, this research consolidation tool works with outputs from Claude Opus 4.6, Gemini 3.1 Pro Deep Research, GPT-5.2 Deep/Chat, or any combination of AI and human sources to merge findings into a unified report.

The best way to reconcile conflicting information is through automated self-review with 7 mandatory checks. This process applies cross-model reconciliation and quality scoring to produce a synthesized, provenance-enriched report.

For pattern-driven research synthesis, you need to provide your research outputs, references, and a pattern registry. These inputs drive provenance tagging, quality scoring, and the application of pattern-specific templates.