From Raw Documents to AI-Ready Data - Leo Platzer & Jeff Koss

AI Engineer21m 37s
Leo Platzer and Jeff Koss against a black background beside the blue-and-white headline “MAKE DOCUMENTS AI READY”.
0 comments · 0 votesOpen discussionClose discussion
Sign in to join the discussion

    Jeff Koss and Leo Platzer use a manufacturing-company scenario to contrast a successful chatbot pilot over selected files with failures after expanding to a much larger document collection. Stale contracts, duplicates, sensitive material and irrelevant documents can undermine answers even when the model and retrieval pipeline appear to work.

    Jeff Koss demonstrates document classificationClassification assigns an input to one or more defined categories using rules or a learned model., evidence-backed metadata and filters for relevance, sensitivity and freshnessData minimization limits collection, use and retention of information to what is needed for a defined purpose.. Leo Platzer explains why selecting the right data slice matters: repeated or outdated documents can crowd useful evidence out of retrievalRetrieval is the process of selecting relevant stored information and returning it to an AI system for the current task. results. Classification confidence still needs review and is not a guarantee of correctness.

    Leo Platzer and Jeff Koss describe maintaining curated collections through an SDK and making context available to agentsContext engineering designs how relevant instructions, evidence, state and tool information are assembled for a model's task. in repository-friendly files. They present retrieval improvements from their own experiments, while the broader lesson is to evaluate data preparation against the actual taskA data pipeline moves information through ordered collection, transformation and delivery steps for use by software or AI. rather than treating more documents as automatically better.

    Original YouTube thumbnailWatch on YouTube

    Video topic coverage

    • Agents & workflows35
    • Coding & tools20
    • Models & learning10
    • Infrastructure & compute100
    • Research & evaluation50
    • Safety & security45
    • Business & productivity35
    • Creative & media0
    • Robotics & perception0
    • Society & policy0

    Share this video

    Leo Platzer and Jeff Koss against a black background beside the blue-and-white headline “MAKE DOCUMENTS AI READY”. With WWW.ARTIFICIAL-INTELLIGENCE.VIDEO, 5 October 2026 and duration 21m 37s.

    Leo Platzer and Jeff Koss demonstrate how governed metadata and quality filters can turn sprawling document collections into more useful AI retrieval inputs.