Use case

Which data is redundant?

Duplicate and overlapping knowledge bloat context and confuse retrieval. Kno flags redundancy explicitly as a rejection reason, with the asset it duplicates.

The problem

Every knowledge base accretes near-duplicates: the FAQ page that restates the policy, the example that repeats an older one. Redundancy steals budget from data that earns it, and no one notices because no one measures.

The workflow

1. Value

   Each asset is measured on its own; near-identical assets produce overlapping effects.

2. Select

   The selection pass rejects redundant assets with an explicit reason , e.g. `redundant, duplicates refund-policy`, not silently.

3. Export

   Export only the non-redundant portfolio, keeping the rejection log for your records.

What it looks like

Rejected 1
  old-faq   redundant   duplicates refund-policy

The recipe

Feed the whole candidate pool at once, Kno’s selection stage compares assets against each other, not just against the baseline, and records the rejection log with reasons.

Stages involved

• value
• select
• export