mapped

Vector Spaces and Tensors

How coordinates shapes and transformations represent information numerically.

concept / mapped / current
mapped

Uncertainty and Calibration

How probability estimates express uncertainty and align with outcomes.

concept / mapped / current
mapped

Gradient Descent

How iterative optimization follows local objective information to update parameters.

concept / mapped / current
mapped

Complexity Analysis

How time and space growth guide algorithm and system choices.

concept / mapped / current
mapped

Concurrency Models

How asynchronous tasks threads processes and coordination affect correctness.

concept / mapped / current
mapped

Software Contracts

How interfaces invariants and tests preserve behavior across change.

concept / mapped / current
mapped

Web Rendering and State

How server and browser rendering strategies shape interactive applications.

concept / mapped / current
mapped

Reproducible Delivery

How automated builds tests images and releases create dependable deployments.

concept / mapped / current
mapped

Database Selection

How workload consistency access and scale determine storage choices.

concept / mapped / current
mapped

Data Contracts and Lineage

How schemas quality checks and provenance make pipelines trustworthy.

concept / mapped / current
mapped

Learning Paradigm Selection

How available signals feedback and objectives determine a learning approach.

concept / mapped / current
mapped

Generalization and Leakage

How evaluation design estimates future performance without contaminating evidence.

concept / mapped / current
mapped

Backpropagation

How gradients propagate through computational graphs to train neural networks.

concept / mapped / current
mapped

Computer Vision

Elective branch covering image representation recognition detection and generation.

concept / mapped / current
mapped

Speech and Audio AI

Elective branch covering recognition synthesis understanding and audio generation.

concept / mapped / current
mapped

Recommendation Systems

Elective branch covering ranking personalization feedback and marketplace effects.

concept / mapped / current
mapped

Time-Series AI

Elective branch covering forecasting anomaly detection and temporal decision systems.

concept / mapped / current
mapped

Robotics and Embodied AI

Elective branch covering perception planning control and physical interaction.

concept / mapped / current
mapped

Edge Model Optimization

How compression runtimes and hardware co-design enable constrained inference.

concept / mapped / current
lab

Tokens and Tokenization

How model inputs become discrete identifiers and why token boundaries affect cost and meaning.

concept / lab / current
lesson

Embeddings

How learned vectors encode useful similarity and support representation and retrieval.

concept / lesson / current
lesson

Transformer Architecture

How attention feed-forward blocks residual paths and positions transform sequences.

concept / lesson / current
lesson

Training versus Inference

How parameter learning differs from runtime generation and serving operations.

concept / lesson / current
lab

Context Windows

How finite input and output budgets constrain attention state relevance and cost.

concept / lab / current
lab

Sampling and Decoding

How logits temperature top-p and deterministic choices shape generated sequences.

concept / lab / current
lesson

Model Families and Lifecycle

How capability modality size versioning deprecation and routing affect model selection.

concept / lesson / current
lab

Latency and Throughput

How queueing prompt processing generation batching and concurrency determine serving performance.

concept / lab / current
mapped

Multimodal Fusion

How models align and combine text image audio and video representations.

concept / mapped / current
lesson

Message Roles and Instruction Priority

How instruction sources and ordered messages establish conversational control context.

concept / lesson / current
lesson

Prompt Structure

How clear goals constraints context examples and output contracts guide model behavior.

concept / lesson / current
lesson

Structured Outputs

How schemas convert probabilistic text generation into validated application contracts.

concept / lesson / current
lesson

Tool Calling

How models propose typed actions while applications retain execution authority and validation.

concept / lesson / current
lesson

Context Engineering

How systems select assemble order compress and isolate information for each model call.

concept / lesson / current
lesson

State and Memory

How applications persist working state history summaries facts and user-controlled records.

concept / lesson / current
lesson

Exact and Semantic Caching

How reusable computations reduce latency and cost while introducing freshness and correctness risks.

concept / lesson / current
lab

RAG versus Fine-Tuning

How knowledge access behavior adaptation and tool use solve different system problems.

concept / lab / current
lab

Ingestion and Chunking

How parsing normalization segmentation metadata and updates create retrievable units.

concept / lab / current
lab

Vector Search

How embeddings similarity indexes filters and recall tradeoffs retrieve semantic candidates.

concept / lab / current
lab

Hybrid Search and Reranking

How lexical semantic and learned ranking stages improve candidate precision and recall.

concept / lab / current
lesson

Grounded Generation and Citations

How answer synthesis constrains claims to evidence and preserves inspectable attribution.

concept / lesson / current
mapped

Knowledge Provenance

How origin ownership version and transformation metadata make knowledge auditable.

concept / mapped / current
mapped

Agent Control Loop

How bounded observe decide act and verify cycles produce controlled autonomy.

concept / mapped / current
mapped

Workflow Orchestration

How explicit state transitions coordinate repeatable AI and software work.

concept / mapped / current
mapped

Context and Tool Protocols

How standardized discovery invocation and data exchange connect model systems.

concept / mapped / current
mapped

Human Approval Boundaries

How consequence and reversibility determine when human authorization is mandatory.

concept / mapped / current
mapped

AI Feedback and Correction

How interfaces expose progress uncertainty evidence and correction controls.

concept / mapped / current
mapped

Streaming AI Interfaces

How incremental transport cancellation state and recovery create responsive experiences.

concept / mapped / current
lab

LLM Evaluation

How task definitions datasets metrics rubrics judges and experiments measure system quality.

concept / lab / current
lesson

Grounding and Hallucination

How unsupported claims arise and how evidence constraints and verification reduce them.

concept / lesson / current
mapped

AI Tracing

How correlated model retrieval tool and application spans expose system behavior.

concept / mapped / current
lab

Cost Latency and Reliability

How budgets fallbacks retries routing and service targets balance operating outcomes.

concept / lab / current
lesson

Security and Privacy for LLM Systems

How untrusted inputs sensitive data tools and external knowledge expand the threat model.

concept / lesson / current
mapped

Safety Evaluation and Response

How adversarial tests policy checks monitoring and response control harmful behavior.

concept / mapped / current
mapped

AI Risk Governance

How ownership classification documentation and review control lifecycle risk.

concept / mapped / current
mapped

Inference Serving Architecture

How routing batching caching autoscaling and accelerators serve model workloads.

concept / mapped / current
mapped

AI Unit Economics

How per-task value quality compute tokens and operational costs determine viability.

concept / mapped / current
mapped

Capability-Problem Fit

How uncertain model capabilities map to valuable testable user outcomes.

concept / mapped / current
mapped

Evidence Synthesis

How primary sources experiments and explicit confidence create durable knowledge.

concept / mapped / current
mapped

Information Entropy

How entropy and information measures describe uncertainty compression and representation.

concept / mapped / current
researched

Predictive Processing

What hierarchical prediction and prediction error propose about perception and what AI engineers must not infer.

concept / researched / current
mapped

Cognitive Architectures

How cognitive models decompose memory reasoning attention and action without becoming literal brain replicas.

concept / mapped / current
mapped

Language and Thought

How language structures communication and reasoning without equating fluent generation with complete understanding.

concept / mapped / current
mapped

Philosophy of Intelligence

How competing definitions of intelligence change system claims evaluation and responsible communication.

concept / mapped / current
mapped

Evidence and Replication

How to distinguish a result from a durable claim through replication synthesis and explicit uncertainty.

concept / mapped / current
mapped

Causal Inference

How interventions assumptions and identification separate causal questions from predictive accuracy.

concept / mapped / current
mapped

Reinforcement Learning

How policies learn sequential decisions from feedback and where reward design and distribution shift fail.

concept / mapped / current
mapped

Full-Stack AI Systems

How interfaces APIs orchestration data and model providers form one observable product system.

concept / mapped / current
researched

Inference Engine Architecture

How schedulers KV-cache managers model runners and distributed executors determine serving behavior.

concept / researched / current
mapped

MLOps Lifecycle

How versioned artifacts evaluation promotion monitoring rollback and retirement make model changes governable.

concept / mapped / current
mapped

Distributed AI Systems

How computation communication memory placement and failure domains shape large-scale AI platforms.

concept / mapped / current
mapped

AI System Testing

How to combine deterministic software tests model evaluations adversarial checks and monitored production evidence.

concept / mapped / current
mapped

Organizational AI Change

How capability ownership workflow redesign governance and feedback determine whether AI adoption produces value.

concept / mapped / current
researched

Clinical Decision Support

How AI recommendations enter clinical workflows and why evidence oversight usability and escalation determine safety.

concept / researched / current
mapped

AI in Financial Risk

How AI changes fraud risk and underwriting workflows under model-risk and consumer-protection constraints.

concept / mapped / current
mapped

AI-Assisted Learning

How AI can support practice feedback and synthesis without replacing learner effort or reliable assessment.

concept / mapped / current
mapped

AI for Scientific Discovery

How AI can accelerate search and experiment cycles while preserving measurement validity and reproducibility.

concept / mapped / current
mapped

AI-Assisted Software Engineering

How AI changes software throughput review burden system understanding and security risk.

concept / mapped / current
mapped

Industrial AI Automation

How AI interacts with physical constraints safety cases latency and operational recovery in industry.

concept / mapped / current
mapped

AI for Climate and Energy

How forecasting optimization and sensing support resource decisions while computation and rebound costs remain visible.

concept / mapped / current
mapped

Generative Media Systems

How models production tools rights provenance and human direction combine in responsible media systems.

concept / mapped / current
mapped

AI in Law and Public Services

How automation affects accountable decisions rights access explanation appeal and institutional legitimacy.

concept / mapped / current
mapped

AI Labor and Society

How AI changes tasks bargaining power institutions distribution and competitive dynamics beyond headline job counts.

concept / mapped / current
lesson

LLM Systems Foundations

Build a connected mental model from tokens through retrieval evaluation security and operations.

path / 18 hours
lab

Tokenization and Context Window Visualizer

Inspect deterministic token approximations and allocate a finite context budget.

lab / version 1
lab

Sampling and Decoding Explorer

Explore how temperature and top-p reshape a fixed token distribution.

lab / version 1
lab

Prompt RAG Fine-Tuning or Tool-Use Decision Lab

Match system symptoms and constraints to an appropriate intervention strategy.

lab / version 1
lab

RAG Pipeline and Retrieval Parameter Visualizer

Tune chunk size retrieval breadth hybrid weight and reranking in a deterministic pipeline.

lab / version 1
lab

LLM Cost Latency and Reliability Simulator

Model request economics latency percentiles and fallback effects under disclosed assumptions.

lab / version 1
lab

Evaluation Strategy Designer

Assemble a balanced evaluation plan from risks cases metrics review and release gates.

lab / version 1
guide

LLM Application Boundaries

Separate model behavior, application policy, tools, state, and validation into testable system boundaries.

architecture guide
guide

Retrieval System Design

Trace ingestion, chunking, search, reranking, generation, citations, and evaluation as one evidence pipeline.

architecture guide
guide

Agent Control Paths

Design tool authorization, state, memory, failure handling, and human control around probabilistic decisions.

architecture guide
guide

Reliable AI Operations

Connect evaluation, latency, throughput, cost, privacy, security, monitoring, and release decisions.

architecture guide
researched

Grounded Research Assistant

Build an evidence-carrying RAG workflow with hybrid retrieval, reranking, citations, evaluation, and abstention.

project / intermediate
researched

Governed Tool-Using Agent

Build an agent with schema-validated tools, independent authorization, state, retries, audit events, and human approval.

project / advanced
researched

AI Support Workspace

Connect a streaming interface, conversation state, retrieval, tool execution, observability, and operating-cost controls.

project / advanced