ADR-008: Use Azure AI Foundry (serverless) for LLM inference
Context
Context
Context
Why Aucert has no LLM models running in AKS — and where they actually run
How to call Aucert's LLM models from local dev, AKS pods, and CI/CD
How Aucert routes AI workloads across model tiers for cost optimization and quality balancing
How spec-agent (atlas) selects models, how operators override the default via comment tags, and how reply prefixes identify which model answered