Topic
Built an internal AI knowledge assistant and the RAG ingestion and evaluation pipeline behind it for a telecom BSS platform, so technical consultants get grounded answers instead of digging through wikis. Exact figures and architecture inside.
Read case studyRan the security testing for a regional telecom operator's AI product release and produced the client-facing disclosure and report that turned scan output into a rollout decision, plus a standing re-scan gate. Tooling and findings inside.
Read case studyTurned an autonomous AI content pipeline from mostly-unusable to mostly-passing by encoding success criteria as machine-readable intent specs, with a maker and judge loop and a scored quality gate. Exact pass rates inside.
Read case studyBuilt a production retrieval-augmented knowledge base over a large multi-repository engineering codebase and document corpus, with dual embeddings, header-aware chunking, and a medallion pipeline. Exact scale and architecture inside.
Read case study