grok14ENGINEERING FIELD SCHOOL
Reference library

References you can build on.

Official platform documentation, terminology notes, and a concise glossary for the course.

MLflow evaluation and monitoring

Current GenAI tracing/evaluation workflow; distinguish managed and preview features.

Read official documentation

Declarative Automation Bundles

Versioned project/resource definitions and the validation/deployment lifecycle.

Read official documentation

Translate older job descriptions

Older or posting termCurrent teaching approach
Vector SearchOfficial documentation uses AI Search; verify SDK/import names separately.
Asset BundlesOfficial documentation uses Declarative Automation Bundles.
AI GatewayCurrent governance overview uses Unity Gateway; verify interface-specific controls.
Agent EvaluationUse current MLflow 3 workflows and distinguish local from managed features.
DBRXUnderstand the posting’s model example; select supported models based on task evidence.

A compact glossary

TermMeaning
FDEForward deployed engineer: an engineer working close to client workflows and delivery constraints.
RAGRetrieval-augmented generation: supplying relevant evidence to a generation step.
EntitlementA verified permission to access a resource or perform an action.
IdempotencyA repeated logical operation has the intended one-operation effect under a defined contract.
TraceA connected record of the application operations for a request.
Held-out setEvaluation cases reserved from the tuning/development loop.
p95 latencyA latency threshold covering roughly 95% of observed requests under a stated calculation.
Data grainThe meaning of one row in a table.
ADRArchitecture decision record: context, alternatives, choice, evidence, and consequences.
RunbookAn operational procedure for diagnosis, containment, recovery, and verification.

Keep evidence current

Platform terminology references were checked on 5 October 2026. Product names, previews, regions, permissions, SDKs, and prices can change. Verify exact implementation details when performing a lab. The educational sequence and grading standards are independent design choices, not official certification requirements.

Managed Databricks labs have not been executed as part of this static website package. The bundled Python reference has local verification and clearly stated limits.