Map evidence sources and signals to each dimension
Packaged know-how that tells an agent how to do a job well.
You might say…
“Mapping sources to dimensions before the first live case meant I'd already solved the 'where do I look for this?' problem before it became a time pressure.”
What it does
For each scoring dimension, proposes named sources, the specific data point or signal to extract from each, and a fallback for common data gaps.
Trigger: Use after dimensions and rubric levels exist, to produce the evidence guide analysts follow during data collection.
I/O: Locked dimension set + rubric → per-dimension evidence guide listing named sources, extraction signals, and data-gap fallbacks
Recognise the problem?
The primitives are the commodity part. The fastest next step is a conversation about composing them into something that works for you.
Start a conversation