Play Browser · 101 plays
Solution plays
Production-grade FAI Protocol plays. Each ships with a manifest, infrastructure code, primitives, and an evaluation suite. All MIT.
Filter
81 of 101 playsClear filters
- 12-model-serving-aksmediumOptimize GPU utilization, spot node pools, auto-scaling rules, quantization level, batch size
Optimize GPU utilization, spot node pools, auto-scaling rules, quantization level, batch size
- primitives
- 10
- waf
- 4
- industry
- general
- azure
- 14-cost-optimized-ai-gatewaymediumOptimize cache TTL, similarity threshold, PTU vs pay-as-you-go, routing rules, cost per request
Optimize cache TTL, similarity threshold, PTU vs pay-as-you-go, routing rules, cost per request
- primitives
- 10
- waf
- 4
- industry
- general
- azure
- 15-multi-modal-docprocsmallOptimize vision vs OCR routing per page type, image resolution, batch throughput, cost per document
Optimize vision vs OCR routing per page type, image resolution, batch throughput, cost per document
- primitives
- 10
- waf
- 3
- industry
- general
- azure
- 16-copilot-teams-extensionsmallOptimize Adaptive Card layouts, response quality, Graph API batching, caching strategy
Optimize Adaptive Card layouts, response quality, Graph API batching, caching strategy
- primitives
- 10
- waf
- 3
- industry
- developer-tools
- azure
- 17-ai-observabilitysmallOptimize sampling rates, log retention tiers, alert thresholds, dashboard query performance, storage cost
Optimize sampling rates, log retention tiers, alert thresholds, dashboard query performance, storage cost
- primitives
- 10
- waf
- 3
- industry
- general
- azure
- 18-prompt-managementsmallOptimize prompt token usage, A/B test analysis, template compression, few-shot example selection
Optimize prompt token usage, A/B test analysis, template compression, few-shot example selection
- primitives
- 10
- waf
- 3
- industry
- general
- azure
- 19-edge-ai-phi4smallOptimize quantization level (INT4/INT8), inference speed, prompt compression, battery impact, cloud sync frequency
Optimize quantization level (INT4/INT8), inference speed, prompt compression, battery impact, cloud sync frequency
- primitives
- 10
- waf
- 3
- industry
- general
- azure
- 20-anomaly-detectionsmallOptimize sensitivity thresholds, reduce false positives, tune detection windows, alert fatigue reduction
Optimize sensitivity thresholds, reduce false positives, tune detection windows, alert fatigue reduction
- primitives
- 10
- waf
- 3
- industry
- general
- azure
- 21-agentic-raglargeOptimize source selection weights, iteration thresholds, cache hit rates, cost per query, max retrieval hops
Optimize source selection weights, iteration thresholds, cache hit rates, cost per query, max retrieval hops
- primitives
- 11
- waf
- 5
- industry
- general
- azure
- 22-multi-agent-swarmlargeOptimize swarm size, agent selection strategy, voting thresholds, parallel vs sequential, cost per task
Optimize swarm size, agent selection strategy, voting thresholds, parallel vs sequential, cost per task
- primitives
- 11
- waf
- 5
- industry
- general
- azure
- 23-browser-automation-agentmediumOptimize step count, wait strategies, selector resilience, screenshot resolution, action success rate
Optimize step count, wait strategies, selector resilience, screenshot resolution, action success rate
- primitives
- 11
- waf
- 4
- industry
- general
- azure
- 24-ai-code-review-pipelinemediumOptimize review prompts, reduce noise/false positives, tune severity thresholds, model routing for cost
Optimize review prompts, reduce noise/false positives, tune severity thresholds, model routing for cost
- primitives
- 10
- waf
- 4
- industry
- developer-tools
- azure