Patterns
Implementation control library
Find the implementation control behind the gap.
138 implementation controls mapped to architecture, obligations and evidence. Search the problem; open implementation depth only when you need it.
A/B Model Evaluation
Upgrading the LLM powering a production AI application carries risk that cannot be fully characterised in offline eval…
EAAPL-OBS006 · AI Cost Observability
AI inference costs have a fundamentally different cost structure than traditional compute: they are token-based, per-r…
EAAPL-OBS004 · AI Incident Management
AI system failures are qualitatively different from traditional software failures. An AI system can be operationally a…
EAAPL-OBS008 · AI Performance Benchmarking
AI system quality degrades silently between benchmarking events. A model that scored 87% accuracy in its pre-deploymen…
EAAPL-OBS001 · AI Telemetry Architecture
AI systems present unique observability challenges that traditional APM tooling does not address. Unlike deterministic…
EAAPL-OBS007 · Distributed AI Tracing
AI pipelines are not single API calls. They are chains of components — authentication, rate limiting, prompt assembly,…
EAAPL-OBS003 · Hallucination Detection
Large language models fabricate plausible-sounding content with confidence. In enterprise settings, a hallucinated leg…
LLM Evaluation Pipeline
Deploying an LLM update to production without a structured evaluation gate is equivalent to deploying software without…
EAAPL-OBS005 · Model Drift Detection
AI models degrade silently. Unlike a server that crashes with a clear error, a drifting model continues returning HTTP…
Prompt Drift Detection
LLM providers update their underlying models without breaking API contracts. A prompt that achieved 92% faithfulness o…
EAAPL-OBS002 · Prompt Monitoring
Prompts sent to large language models in production are the primary control surface for AI system behaviour, yet most…