Gemini Enterprise adds latency and error rate observability for agents
Gemini Enterprise has launched new observability views within its platform, enabling users to monitor the operational telemetry of their agents. These views provide detailed insights into latency, including p50 and p95 metrics for Time to First Token, Time to First Answer, and Time to Last Token. Additionally, an error rate view tracks request volume, categorizing issues by response class and detailing client/server error codes. This functionality is now generally available, helping developers and operators diagnose agent performance.
Features (1) ›
- Gemini Enterprise Gemini Enterprise: Latency and error rate views for agents
Gemini Enterprise: Latency and error rate views for agents To monitor operational telemetry for your agents, use the two new views on the Observability tab: Latency: Shows response times for your agents. This view displays p50 (median) and p95 (95th percentile) metrics for Time to First Token (TTFT), Time to First Answer (TTFA), and Time to Last Token (TTLT). TTFT counts the first token of any kind, including the model's thinking, while TTFA counts only the first token of the answer itself. You can also compare latencies by specific agent features, such as web search, media generation, or para
https://docs.cloud.google.com/release-notes#September_03_2026
Related releases
- BigQuery Conversational Analytics Adds Market Basket Analysis Support Google Cloud release notes ·
- Spanner Adds PostgreSQL-Dialect ILIKE and NOT ILIKE Operators Google Cloud release notes ·
- API Gateway Updates Default Hostname Format for Model Routing Google Cloud release notes ·
- Google Cloud expands Data Cloud with real-time analytics, AI, and open tables Google Cloud Blog ·
- GCP Compute Engine Previews Advanced Images for AI/ML/HPC Workloads Google Cloud release notes ·
- Client-Side Metrics for Memorystore for Redis Now GA Google Cloud release notes ·