5-layer pipeline deep dive
Complete internal architecture of Aucert's 5-layer AI quality pipeline with MCP protocol, code paths, and model assignments
14 docs tagged with "architecture"
View all tagsADR-001: Single monorepo over multi-repo
Context
ADR-003: Monolith-first backend
Context
ADR-004: ML as top-level workspace
Context
ADR-005: PostgreSQL+JSONB for Knowledge Graph MVP
Context
ADR-007: public/ for publishable packages
Context
ADR-009: LLM model selection strategy for the 5-layer testing pipeline
Context
ADR-015: ID Generation Strategy — UUIDv7 Primary Keys and NanoId Handles
Context
Azure AI Foundry architecture
Why Aucert has no LLM models running in AKS — and where they actually run
Device Twin architecture
Internal architecture of the AI Device Twin — calibration, prediction, and confidence adjustment for emulator-to-device divergence
Knowledge Graph internals
Internal architecture of the Aucert Knowledge Graph engine — data model, storage, ingestion pipeline, and query patterns
Model orchestration
How Aucert routes AI workloads across model tiers for cost optimization and quality balancing
Validation Graph — design walkthrough
Interactive walkthrough of the Validation Graph design (SPEC-035) — two-graph knowledge layer, substrate, ACL, conditions, embeddings, deployment, tech choice
Verification Cascade
4-stage confidence-gated verification system for minimizing false positives with cost-aware escalation