Enterprise Knowledge Search · IT Operations Automation · Real-time Analytics
Kogan.com needed to eliminate brittle export-based BI pipelines, shorten slow answer cycles for business users, and expose analytics conversationally without losing semantic consistency or data-level security.
Reported impact
Kogan.com cut data turnaround to seconds, turned more than a hundred non-technical users into self-service analysts, and reduced maintenance burden by grounding conversational analytics in a tested semantic model instead of fragile export scripts.
Kogan.com reorganized around a data-engineering-first analytics stack on Google Cloud, using BigQuery, dbt, and Looker as the governed core and then exposing that core through conversational AI. Raw staging data is funneled into BigQuery, where dbt builds tested fact and dimension tables and manages metadata that automatically surfaces inside Looker. Looker supplies the semantic layer and row-level permissions, while an internal enterprise MCP fleet server with OAuth wraps the open Model Context Protocol architecture so AI agents can query only the data a user is authorized to see. Batch jobs and transformations also run directly in BigQuery to keep costs controlled. The result is an environment where non-technical teams can ask questions through text, get secure instant answers from curated datasets, and hand dashboards back into Looker for shared use, rather than waiting on a reactive BI ticket queue.
Operational retail data is loaded into BigQuery, transformed by dbt into facts and dimensions, and surfaced in Looker. Employees then query that semantic layer through an OAuth-protected MCP fleet server, which enforces Looker permissions before returning conversational answers or dashboards.
By unifying dbt and Looker, Kogan.com created a highly optimized, cost-effective data pipeline.
Data turnaround dropped from 40 minutes to under 60 seconds
This zero-trust approach mandates user authentication before granting server access
connected their curated BigQuery datasets and Looker’s semantic layer directly to internal AI agents through an enterprise Model Context Protocol (MCP) fleet server
transforming 150 non-technical team members into independent, data-driven vibe coders
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
Google Cloud Sample Modified · Aug 20, 2026 Carrefour Maximum cost-efficiency with scale-to-zero: Hosting on Cloud Run ensures the infrastructure completely shuts down at night and on weekends, reducing operational costs to the absolute minimum Carrefour transformed internal support by deploying a serverless, RAG-based AI assistant in Google Chat,… Agent Development Kit (ADK) · Agent Platform · BigQuery Google Cloud Sample Archived · Aug 19, 2026 Wayfair Wayfair needed to reduce developer context switching and long CI failure recovery times by giving engineers fast, contextual explanations and fixes inside the tools they already use. 58% reduction in Mean Time To Recovery (MTTR), from 26 minutes to 11 Buildkite · Gemini · Gemini platform Google Cloud Sample Modified · Aug 6, 2026 Trade Me Trade Me wanted to turn a marketplace and engineering organization into an AI-first ecosystem, which meant replacing physical data centers, accelerating incident diagnosis, and letting employees query marketplace trends… Achieved 4 9s availability for critical APIs through Agent Development Kit · AlloyDB · BigQuery 