Batch Inference Job Control for AI Pipelines
Build a .NET batch inference runner with request manifests, idempotency keys, retry envelopes, checkpoints, failed-row quarantine, and replayable output records backed by Microsoft Foundry.
Technical library
Articles
Long-form AI engineering articles for systems, workflows, architecture, and production decisions.
4published articles
Sep 26, 2026latest update
Browse by topic
Choose a topic to focus the library.
Runtime & Operations
4 articles found
Runtime & Operations
4 articlesStreaming AI Gateways
Build a .NET streaming AI gateway with server-sent events, cancellation handling, partial-output policy, and finalization records before streamed text is treated as committed.
AI Cost Engineering for Local Inference
Build a local-first inference gateway with exact cache keys, per-tenant budget reservation, sync-vs-batch routing, deferred execution, and measurable cost controls in C#.
Production Reliability Engineering for AI APIs
Build a local-first inference gateway with deterministic rate limiting, queue backpressure, retries, timeouts, circuit breakers, fallback routing, and measurable runtime reliability metrics.