Flexible path9 sections

AI Engineering

Applied AI interview preparation grounded in real product and production decisions.

A practical AI engineering path covering model fundamentals, structured output, retrieval, evaluation, application architecture, managed cloud platforms, agents, security, and production diagnosis.

Recommended start

AI Fundamentals

Models, tokens, context, sampling, embeddings, limitations, model selection, and dependable application boundaries.

20 drillsSection 1 of 9

Open section Browse all drills

Learning path

9 active sections / 160 drills

1AI FundamentalsRecommended startModels, tokens, context, sampling, embeddings, limitations, model selection, and dependable application boundaries.20 drillsSection 1Open section 2Prompting & Structured OutputInstruction hierarchy, context construction, schemas, validation, tool calls, and output repair.20 drillsSection 2Open section 3RAG & Vector SearchChunking, embeddings, retrieval, ranking, grounding, citations, freshness, and access control.18 drillsSection 3Open section 4AI Evaluation & ObservabilityDatasets, graders, traces, quality metrics, regressions, production feedback, and release evidence.18 drillsSection 4Open section 5AI Application ArchitectureGateways, orchestration, state, deterministic controls, fallbacks, versioning, and reliable workflows.18 drillsSection 5Open section 6Managed AI Platforms & Cloud ServicesManaged models, retrieval, agents, gateways, guardrails, regions, quotas, cost controls, and portability.16 drillsSection 6Open section 7Agents & WorkflowsTool use, planning, state, memory, permissions, approval, recovery, and agent evaluation.18 drillsSection 7Open section 8AI Security, Privacy & GovernancePrompt injection, data leakage, tenant isolation, tool authorization, provenance, retention, audit, and policy.20 drillsSection 8Open section 9AI Production Scenarios & LabsFocused implementation, debugging, evaluation, incident response, and architecture-review exercises.12 drillsSection 9Open section