{"slug": "from-question-first-to-analyst-first-domain-expert-skills-and-verified-knowledge", "title": "From Question-First to Analyst-First: Domain-Expert Skills and Verified Knowledge Compilation for Proactive Enterprise Analytics", "summary": "Researchers describe a production analytics system that inverts the interaction model from question-first to analyst-first, using a pluggable domain-expert 'skill' abstraction and an offline knowledge-compilation loop that probes datasets via DuckDB to produce verified schema knowledge and standing expert reports. The system, detailed in arXiv:2608.28594v1, aims to help non-expert users by auto-selecting subject-matter packs per client and dataset, and re-verifying every published metric by re-executing its evidence SQL. The authors make no user-study or benchmark claims, focusing instead on the architecture and its defensibility.", "body_md": "arXiv:2608.28594v1 Announce Type: new\nAbstract: Conversational analytics systems assume the user already has a well-formed question, leaving a non-expert facing a blank query box on an unfamiliar enterprise schema. Commercial 'proactive' tools narrow this gap only by detecting statistical anomalies over analyst-curated metric layers, and academic next-question recommenders depend on query logs that a fresh dataset lacks. We describe a production analytics system that inverts the interaction model from question-first to analyst-first through two coupled architectural ideas. First, a pluggable domain-expert 'skill' abstraction: a folder-based, database-free subject-matter pack (a manifest, per-stage prompt facets, keyword-routed references, report templates, and optional compute) auto-selected per (client, dataset) by deterministic schema matching and spliced as a cross-cutting concern into every stage of an agentic pipeline, the schema explorer, and the report engines, degrading to a strict no-op when absent. Because a skill is a self-contained folder resolved deterministically, the catalogue is open-ended: an extensible marketplace of domain experts. Second, an offline knowledge-compilation loop: an agent probes the dataset's parquet via DuckDB (zero load on production), runs critic-gated per-table convergence with self-healing retries, and data-validates joins by value overlap, producing durable schema knowledge that drives standing expert reports whose every published metric is re-verified by re-executing its evidence SQL, plus suggested questions that mirror the report agenda. These close a proactive loop: reports surface numbers, the numbers seed questions, and a click launches a verified deep dive, all before the query box is used. We give a formal model and report illustrative single-tenant evidence. We make no user-study or benchmark claims; the contribution is the architecture and its defensibility.", "url": "https://wpnews.pro/news/from-question-first-to-analyst-first-domain-expert-skills-and-verified-knowledge", "canonical_source": "https://arxiv.org/abs/2608.28594", "published_at": "2026-09-01 04:00:00+00:00", "updated_at": "2026-09-01 04:26:31.469645+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "ai-infrastructure"], "entities": ["arXiv", "DuckDB"], "alternates": {"html": "https://wpnews.pro/news/from-question-first-to-analyst-first-domain-expert-skills-and-verified-knowledge", "markdown": "https://wpnews.pro/news/from-question-first-to-analyst-first-domain-expert-skills-and-verified-knowledge.md", "text": "https://wpnews.pro/news/from-question-first-to-analyst-first-domain-expert-skills-and-verified-knowledge.txt", "jsonld": "https://wpnews.pro/news/from-question-first-to-analyst-first-domain-expert-skills-and-verified-knowledge.jsonld"}}