KDDI shares how it optimized its Buffmee RAG app on Google Cloud
AIMade by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made
Shared a case of optimizing its consumer RAG app Buffmee with the Google Cloud stack. Buffmee answers on the basis of more than 100 sources, including books, magazines and web media, and cites its sources; it uses the Gemini Enterprise Agent Platform evaluation service, Agent Development Kit, BigQuery Agent Analytics and Agent Search. By switching to binary pass/fail evaluation metrics, introducing strategic sampling based on a two-dimensional grid of file format × media composition, and splitting a system prompt of more than 800 lines into ADK Skills modules, the company says it achieved a 38% reduction in overall response latency, about an 18% improvement in TTFT, a 25% gain in groundedness and a 75% cut in evaluation workload.
Why it matters
A case showing in numbers that agent quality improves not by swapping models but through the engineering discipline of evaluation systems and prompt modularization.
Source — Primary sources first; secondary reports are labelled “Press”
Officialcloud.google.comhttps://cloud.google.com/blog/topics/customers/how-kddi-optimized-rag-performance-with-agent-development-kit/Added in Week 38, 2026 · See that week
On the map — ② RAG, Fine-Tuning line
- Previous stopMartin and Roger publish Classifier Context Rot
- This record · stopKDDI Buffmee
- Next stopNo later stop yet