context-mastery

To route complex technical tasks to the right capability, analyze the task requirements to select the smallest sufficient capability from available mental models, learning navigators, and decision-builders. This ensures efficient problem-solving for unfamiliar system architectures.

Maintaining evidence-linked provenance for domain learning outputs requires grounding all generated artifacts in provided evidence. This approach preserves transparency and strict validation boundaries while coordinating expert decision-making capabilities.

You need context routing for unfamiliar system architecture tasks when facing high-stakes delivery cases or review-gap discovery. It determines whether you require a system mental model, a learning path, or a decision-question packet to proceed safely.

Yes, you can use context routing for bounded tasks within complex technical environments. It applies to feature delivery cases and review-gap discovery, requiring adherence to strict validation and permission boundaries while selecting optimal capabilities.

Intelligent routing selects the smallest sufficient capability by analyzing task requirements against a suite of mental models, learning navigators, and decision-builders. This coordinates the optimal capability for expert decision-making and domain learning.

Context fragmentation causes inefficient problem-solving in technical environments by distributing critical information across disconnected capabilities. Routing high-stakes tasks to the most appropriate specialized capability consolidates context and ensures evidence-linked outputs.