Technical playbooks and shorter posts on retrieval, agents, and production search.
From Q&A chatbots to systems that independently plan, retrieve, act, and verify. Latency, cost, quality tradeoffs at each stage.
How Qdrant's native MMR balances similar results with diverse results for better retrieval quality.
Reproducible RAG evaluation using Qdrant for retrieval and Relari for real-world performance assessment.
NBA stats, Balatro, and the cost of curiosity. Eight iterations of benchmark design, from kitchen sink to meaningful model separation.
Transparency, control, and building agents that search with intention rather than brute force.
Turning scanned documents into a searchable knowledge base with OCR + vector indexing.
Breaking echo chambers in search results using the DeepFashion dataset as a proving ground.