Use cases
Data questions, answered with measurement
Each use case is a question you can hand to Kno today — with the stages that answer it and a recipe to follow.
Which examples deserve space in my context window?
Context windows are a budget, not a box. Kno ranks candidate examples and policies by improvement per token, then selects the portfolio that fits.
Which conversations should I fine-tune on?
Fine-tuning amplifies whatever you feed it, including mistakes. Measure which examples actually improve the agent before they become weights.
Which data is actively hurting my agent?
Some data makes the agent worse, contradictory policies, outdated examples, mismatched tone. Kno measures regression separately from improvement, so harm shows up even when gains exist elsewhere.
Is this policy actually improving my agent?
Policies shape every answer an agent gives. Measure a proposed policy change against real cases before, and after, it goes live.
Which documents should go into my RAG system?
Score each candidate document against your own evals before it reaches the knowledge base, and export the keepers as a manifest.
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.
Which knowledge sources actually help my support agent?
Mine your real support transcripts into an eval set, then measure which help-center pages, policies, and canned answers move real cases.