TENCONIC JOURNAL
Ideas, questions, and practical guides for putting enterprise AI to work.
20 articles
AI foundations
Character counts alone are not a reliable budget for Korean AI workloads. Measure the document, instructions, conversation, and tool descriptions in the actual request, while reserving space for the response.
AI foundations
Two services using the same model can produce different business outcomes. Compare the evidence supplied, access rules, review process, and recovery behavior alongside the model. This guide turns a demonstration into a practical purchasing test.
Company knowledge
Check source versions, ingestion, indexed content, and final model input when RAG quotes old policies. Includes a practical document update test checklist.
Memory & personalization
Diagnose why AI loses earlier conversations or work decisions across storage, retrieval, context, and updates. Compare long context, RAG, and memory, then prepare a practical evaluation.