metacog-imagine

Metacognitive imagination improves AI agent forecasting by analyzing knowledge graphs to identify high-heat entities and knowledge gaps. This process enables forward-looking predictions and proactive planning for long-horizon scenarios.

Trigger counterfactual simulations and scenario analysis by calling the memory.metacog.trigger function with the type parameter set to imagination. This initiates the workflow to generate exploratory questions and forward-looking scenarios.

Yes, you can use knowledge graphs to identify knowledge gaps for risk assessment. The skill probes these gaps by applying value-gating to surface relevant entities and generates exploratory questions to expand understanding.

The best way to maintain a coherent memory cascade during long-horizon planning is by integrating with CoreMemory. This allows the system to append insights from counterfactual simulations and external data sources continuously.

Yes, the forecasting approach satisfies integration with UHMSBridge. This integration supports the memory-driven outcomes and counterfactual reasoning required across large knowledge bases.

You should avoid using metacognitive imagination for scenario analysis if your AI agent lacks an existing knowledge graph or if the task does not require long-horizon planning, risk assessment, or counterfactual reasoning capabilities.