SERIES_OVERVIEW // CURRICULUM_MAP

Learn Python AI Application Engineer

// Kaufman skill map untuk membongkar Python AI Application Engineering menjadi subskill yang bisa dilatih, diukur, dan dipakai membangun AI application production-grade.

This track is ordered for sequential learning. Start from the first part if you want the full mental model, or jump directly into a chapter if you already know the foundations.

START FROM PART 01 JUMP TO LATEST PART

Total Parts

Reading Load

512

MIN TOTAL

Estimated Commitment

8.5 HOUR LEARNING TRACK

35 PARTS512 MIN TOTALagentic-systemsagentsaiai-application-engineeringai-engineeringapplication-architecture

Curriculum Map

Ordered progression from foundations to advanced topics

PART 0119 MIN

Kaufman Skill Map

Kaufman skill map untuk membongkar Python AI Application Engineering menjadi subskill yang bisa dilatih, diukur, dan dipakai membangun AI application production-grade.

PART 0221 MIN

AI Application Engineer Mental Model

Mental model peran Python AI Application Engineer, batasannya dengan ML/Data/Platform roles, dan cara berpikir production-grade untuk sistem AI probabilistik.

PART 0317 MIN

LLM Application Architecture

Mendesain arsitektur aplikasi LLM end-to-end yang production-grade: boundary, lifecycle request, context, tools, retrieval, eval, observability, reliability, dan governance.

PART 0412 MIN

Python AI Project Architecture

Struktur project Python AI application yang maintainable, testable, observable, eval-first, dan siap production tanpa terjebak framework-first design.

PART 0514 MIN

Model Interface and Provider Abstraction

Model interface and provider abstraction untuk membangun aplikasi AI Python yang tidak terkunci pada satu vendor/model, tetap typed, observable, testable, dan siap production.

PART 0613 MIN

Prompting as Protocol Design

Prompting sebagai protocol design: cara mendesain instruksi LLM yang modular, versioned, testable, auditable, aman, dan bisa dipakai di production AI application.

PART 0714 MIN

Structured Output, Schema, and Validation

Structured output, schema design, validation, repair loops, and typed contracts for production-grade Python AI applications.

PART 0814 MIN

Tool Calling and Function Contracts

Tool calling, function contracts, authorization, idempotency, approval gates, and auditability for production-grade Python AI applications.

PART 0916 MIN

Conversation State and Context Management

Conversation state, context management, memory boundaries, summarization, context packing, and auditability for production-grade Python AI applications.

PART 1013 MIN

Async, Streaming, and Backpressure

Async Python, streaming responses, cancellation, timeout, backpressure, queues, and runtime reliability for production-grade AI applications.

PART 1115 MIN

Embeddings and Semantic Representation

Embeddings, semantic representation, similarity, vector records, embedding pipelines, quality diagnostics, and production retrieval foundations for Python AI applications.

PART 1214 MIN

Document Ingestion and Parsing Pipelines

Production document ingestion and parsing pipelines for AI applications, including source connectors, canonical elements, provenance, metadata, idempotency, quality gates, and regulatory auditability.

PART 1324 MIN

Chunking, Indexing, and Knowledge Modeling

Chunking, indexing, and knowledge modeling for production-grade RAG systems.

PART 1420 MIN

Vector Search, Hybrid Search, and Reranking

Vector search, hybrid retrieval, reranking, filtering, and ranking pipelines for production-grade RAG.

PART 1515 MIN

RAG Pipeline Design

End-to-end RAG pipeline design for production AI applications, including query planning, retrieval orchestration, context assembly, answer contracts, citations, refusal, and observability.

PART 1620 MIN

RAG Failure Modes and Diagnostics

Systematic diagnosis of RAG failure modes across ingestion, chunking, indexing, retrieval, reranking, context assembly, generation, citations, and production operations.

PART 1714 MIN

RAG for Enterprise Knowledge Systems

Enterprise RAG knowledge systems: tenancy, permissions, metadata, source authority, freshness, lineage, governance, auditability, and knowledge operations.

PART 1813 MIN

Agent Mental Model

Agent mental model for production AI applications: perception, planning, tool use, state, memory, policies, autonomy boundaries, and failure control.

PART 1911 MIN

Agent Workflow Orchestration

Agent workflow orchestration with state machines, graph execution, deterministic nodes, model decision nodes, human approval, checkpointing, retries, interrupts, and production tracing.

PART 2013 MIN

Tool Registry, MCP, and Integration Contracts

Tool registry, Model Context Protocol, and integration contracts for safe, typed, observable, and permission-aware AI tool use.

PART 2113 MIN

Agent Memory and Long-Running Tasks

Agent memory and long-running task engineering: working state, durable memory, checkpoints, resumability, interrupts, approvals, retention, privacy, and recovery.

PART 2215 MIN

Multi-Agent Systems and Boundaries

Multi-agent systems and boundaries: when to use multiple agents, coordination patterns, supervisor routing, handoffs, shared state, failure isolation, evaluation, and anti-patterns.

PART 2312 MIN

Evaluation Foundations

Evaluation foundations for production AI applications: eval-first mindset, datasets, rubrics, metrics, regression gates, scenario design, calibration, and release readiness.

PART 2411 MIN

RAG and Agent Evaluation

Practical evaluation for RAG and agent systems: retrieval metrics, groundedness, citation accuracy, tool correctness, trajectory scoring, safety gates, and diagnostic eval reports.

PART 2512 MIN

LLM-as-Judge and Human Review

LLM-as-judge and human review for AI application evaluation: rubric design, calibration, bias control, disagreement handling, adjudication, quality sampling, and review operations.

PART 2610 MIN

Testing AI Applications

Testing AI applications across deterministic code, prompts, structured outputs, providers, RAG, tools, agents, workflows, safety, regression, and CI release gates.

PART 2713 MIN

Observability, Tracing, and Debugging

Observability, tracing, and debugging for production AI applications: GenAI telemetry, prompt/model traces, retrieval traces, tool traces, agent traces, metrics, logs, replay, privacy, and incident diagnosis.

PART 2813 MIN

Reliability Patterns for AI Systems

Reliability patterns for AI systems: timeout budgets, retries with jitter, fallback, circuit breakers, bulkheads, rate limits, backpressure, idempotency, graceful degradation, chaos testing, and operational runbooks.

PART 2915 MIN

Latency, Cost, and Throughput Engineering

Latency, cost, and throughput engineering for production AI applications: token economics, TTFT, streaming, batching, caching, model routing, retrieval budgets, concurrency, queues, and capacity planning.

PART 3017 MIN

Security Threat Modeling for LLM Apps

Security threat modeling for LLM applications: prompt injection, data exfiltration, insecure tool use, excessive agency, insecure output handling, RAG poisoning, supply-chain risk, and defense-in-depth.

PART 3113 MIN

Privacy, Governance, and Auditability

Privacy, governance, and auditability for production AI applications: data classification, consent, retention, lineage, DPIA-style review, model/provider governance, audit trails, policy controls, and regulated workflow defensibility.

PART 3214 MIN

Deployment Architecture and Runtime Operations

Deployment architecture and runtime operations for Python AI applications: service topology, model gateway, RAG services, workers, queues, Kubernetes, secrets, rollout/rollback, scaling, health checks, SLOs, and operational runbooks.

PART 3311 MIN

AI CI/CD and Readiness Gates

AI CI/CD and readiness gates for production AI systems: prompt/model/index/tool/workflow versioning, eval gates, security gates, cost gates, release trains, canary, shadow, rollback, and production readiness review.

PART 3413 MIN

Enterprise Case Management AI Capstone

Enterprise case-management AI capstone integrating RAG, agents, tools, evaluation, security, governance, deployment, observability, reliability, and operations into one production architecture.

PART 3518 MIN

Top One Percent Operational Playbook

Top one percent operational playbook for Python AI application engineers: principles, review checklists, incident habits, architecture judgment, decision records, career leverage, and mastery loops.