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
25 of 101 playsClear filters
- 02-ai-landing-zonemediumOptimize SKU sizing, cost, quota, monitoring thresholds, network configuration
Optimize SKU sizing, cost, quota, monitoring thresholds, network configuration
- primitives
- 10
- waf
- 4
- industry
- general
- azure
- 04-call-center-voice-aimediumOptimize response time (STT+LLM+TTS < 2s), model routing, TTS prosody, cost
Optimize response time (STT+LLM+TTS < 2s), model routing, TTS prosody, cost
- primitives
- 10
- waf
- 4
- industry
- general
- azure
- 07-multi-agent-servicemediumOptimize routing rules, per-agent model selection, timeout values, cost per task
Optimize routing rules, per-agent model selection, timeout values, cost per task
- primitives
- 10
- waf
- 4
- industry
- general
- azure
- 09-ai-search-portalmediumOptimize scoring profiles, boost functions, caching strategy, embedding model selection, cost
Optimize scoring profiles, boost functions, caching strategy, embedding model selection, cost
- primitives
- 10
- waf
- 4
- industry
- general
- azure
- 11-ai-landing-zone-advancedmediumOptimize SKU sizing, region selection, policy effects (Audit vs Deny), reserved instances, cost
Optimize SKU sizing, region selection, policy effects (Audit vs Deny), reserved instances, cost
- primitives
- 10
- waf
- 5
- industry
- general
- azure
- 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
- 26-semantic-search-enginemediumOptimize scoring profiles, embedding model selection, query expansion, result re-ranking, cost per query
Optimize scoring profiles, embedding model selection, query expansion, result re-ranking, cost per query
- primitives
- 10
- waf
- 4
- industry
- general
- azure
- 27-ai-data-pipelinemediumOptimize batch sizes, parallelism, LLM enrichment cost, partition strategy, pipeline scheduling
Optimize batch sizes, parallelism, LLM enrichment cost, partition strategy, pipeline scheduling
- primitives
- 10
- waf
- 5
- industry
- data-platform
- azure
- 29-mcp-gatewaymediumOptimize tool descriptions for LLM invocation accuracy, response schemas, transport performance
Optimize tool descriptions for LLM invocation accuracy, response schemas, transport performance
- primitives
- 10
- waf
- 5
- industry
- general
- azure
- 33-voice-ai-agentmediumOptimize response speed, voice quality (prosody/rate), intent accuracy, dialog flow efficiency
Optimize response speed, voice quality (prosody/rate), intent accuracy, dialog flow efficiency
- primitives
- 10
- waf
- 4
- industry
- general
- azure
- 36-multimodal-agentmediumOptimize image detail level, parallel modality processing, cost per multimodal request
Optimize image detail level, parallel modality processing, cost per multimodal request
- primitives
- 10
- waf
- 4
- industry
- general
- azure