Enterprise Knowledge Search · IT Operations Automation
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 without specialized code.
Reported impact
Trade Me shortened triage cycles, improved API reliability, reclaimed staff time from toil, and created a natural-language interface to marketplace intelligence.
Trade Me uses Google Cloud to address this challenge: 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 without specialized code. Gemini Enterprise Agent Platform provides the managed agent runtime that powers internal automation and future engineering-efficiency gains, serving as the serving layer. Agent Development Kit wraps existing APIs and enables specialized agents such as the Incident Agent, serving as the orchestration layer. BigQuery grounds the marketplace agents in operational and trend data that employees can query in natural language, serving as the storage layer. Cloud Run supports the critical APIs that now run with four nines of availability, serving as the serving layer. AlloyDB backs the critical API layer in the cloud-native marketplace stack, serving as the storage layer.
Marketplace and observability data is centralized in BigQuery, ADK-based agents call existing APIs through Gemini Enterprise Agent Platform, Cloud Run and AlloyDB underpin critical marketplace services, and users across the business query trends or incident context in plain English.
Achieved 4 9s availability for critical APIs through
Agents connect directly to BigQuery to extract complex marketplace trends using natural language.
Critical APIs moved from 3 9s to a robust 4 9s of availability.
Slashed incident triage by up to one week with custom Gemini agents built on the Agent Development Kit (ADK).
to extract complex marketplace trends with natural language and decommissioned 100% of physical data centers to modernize operations on
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 · Jun 26, 2026 Kogan.com 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. 150 non-technical team members BigQuery · Looker · Model Context Protocol (MCP) fleet server 