Packs

5 packs

Optimize GKE Costs

Analyzes current usage, recommends cost-saving measures, and applies optimizations to GKE workloads.

3 skills · pack

GKE Batch & Inference

For teams running batch/HPC and AI/ML inference workloads on GKE with specialized hardware.

2 skills · pack

Secure Google Cloud Workload

Assesses security requirements, identifies risks, and provides actionable recommendations for IAM, network, and data protection.

4 skills · pack

Deploy AI Inference on GKE

Deploy and optimize AI/ML inference workloads on GKE using GPUs, TPUs, and model servers.

3 skills · pack

Google Cloud Well-Architected

For architects evaluating Google Cloud workloads against the Well-Architected Framework pillars: reliability, cost optimization, and operational excellence.

6 skills · pack

Results for “workload”

5 skills

enterprise-agent-ops

Operate long-lived agent workloads with observability, security boundaries, and lifecycle management.

graphsignal-profiler

Set up GPU profiling, tracing, and monitoring for inference workloads using vLLM, SGLang, PyTorch, and dstack services via the Graphsignal Profiler sidecar.

More results

Offload sub-tasks to other agents, specialist models, or background jobs, with guidance on choosing the right method and verifying results.

Auto-routes Claude Code subtasks to the cheapest capable model (Haiku/Sonnet/Opus), logs token costs, and A/B tests tiers to validate savings against real workloads.

google-cloud-solution-agentic-ai-bidirectional-streaming

Designs and implements a Google Cloud solution for live, bidirectional multimodal streaming workloads with AI agents, covering requirements discovery, architecture design, and deployment planning.