AI & Agentic Engineering Lessons
104 free, interactive lessons — pick one to read instantly, browse by guide, or generate your own.
Agents
- Autonomous AI Agents Explained
An autonomous AI agent is a system that perceives its environment, decides what to do, acts, and loops — pursuing a goal without step-by-step human instruction.
- The Agent Loop
Understand observe, decide, act, and update as the spine of tool-using agents.
- Multi-agent Orchestration
Split work across specialists only when isolation creates real value.
- Planning and Reflection
Know when planning helps agents and when it only adds latency.
- Agent Memory
Separate thread state, long-term memory, and retrieved knowledge.
- AI Coding Agents: How They Work
An AI coding agent is a language model wired into a reasoning-action loop that lets it plan, write, execute, and iteratively fix code to complete a programming task autonomously.
- Browser and Computer-use Agents
Understand pixel, browser, and DOM action loops plus their safety limits.
- Agent Safety and Sandboxing
Limit blast radius with permissions, sandboxes, approvals, and traces.
- Durable Agents with Workflow Engines
Use durable execution when agent work must survive retries and crashes.
- Human-in-the-loop Agents
Add approvals, review, and correction points to agent workflows.
- Model Context Protocol
Use MCP to expose tools, resources, and prompts through a shared protocol.
- Tool Use and Action Boundaries
Design narrow, auditable tools that agents can call safely.
Build Projects
- Serve a Local LLM with Ollama
Run a local model API and connect it to a simple app workflow.
- Add Observability with Langfuse
Trace model calls, retrieval, tools, scores, and costs end to end.
- Build an Evaluation Harness with promptfoo
Turn prompts and expected behavior into repeatable tests.
- Add Memory to an Agent
Add thread state and long-term memory without confusing memory with facts.
- Build a Document Q&A Bot
Assemble ingestion, retrieval, prompting, citations, and answer validation.
- Build a Tool-Calling Chatbot
Define functions, execute calls safely, and return tool results to the model.
- Build a RAG App with LlamaIndex
Load docs, index chunks, query with sources, and evaluate retrieval.
- Build an Agent with LangGraph
Create a stateful tool-using agent with nodes, edges, and checkpoints.
- Deploy an Open Model with vLLM
Serve an open model with batching, streaming, and production checks.
- Build a RAG App with LangChain
Wire loaders, retrievers, prompts, and model calls into a grounded Q&A flow.
Evaluation
- AI Evaluation Foundations
Turn quality from opinion into repeatable checks, traces, and datasets.
- Benchmark Literacy with HELM
Read public benchmarks without confusing them for product evals.
- Building Golden Datasets
Create reusable examples from real failures and representative user questions.
- Prompt Regression Testing with promptfoo
Run prompt and model tests in CI before release.
- Observability with Langfuse
Trace prompts, retrieval, tools, costs, and scores for LLM apps.
- RAG Evaluation Metrics
Measure context recall, faithfulness, answer relevance, and citation quality.
- Red Teaming LLM Apps
Probe prompts, tools, retrieval, and policies before users do.
- Tracing with OpenTelemetry and OpenLLMetry
Use standard telemetry for model calls, tools, retrieval, and evals.
- Evaluating Agentic Workflows
Score multi-step agents by task success, tool safety, cost, and trace quality.
- LLM-as-Judge
Use model graders carefully for open-ended quality assessment.
Foundations
- Train, Validation, and Test Splits
Learn why clean evaluation starts before model training.
- AI vs ML vs Deep Learning
Understand the nested map of AI, machine learning, deep learning, and where agents fit.
- Embeddings as Learned Representations
Understand how vectors encode meaning for search, clustering, and recommendations.
- Overfitting and Bias-Variance
Diagnose when a model memorizes, underfits, or generalizes.
- Supervised, Unsupervised, and Reinforcement Learning
Pick the right learning paradigm for labels, hidden structure, or reward-driven behavior.
- Feature Engineering and Pipelines
Turn raw data into reliable model inputs without leaking validation data.
- Gradient Descent and Loss Functions
See how models turn errors into weight updates.
- Classic ML Model Zoo
Compare linear models, trees, support-vector machines, neighbors, and clustering.
- Clustering and Dimensionality Reduction
Use k-means, DBSCAN, PCA, and UMAP to explore unlabeled data.
- Neural Networks and Backpropagation
Build the mental model for layers, activations, gradients, and optimizers.
Frameworks
- AutoGen/AG2 and Multi-agent Patterns
Understand conversation-based multi-agent orchestration and its risks.
- Claude Tool Use and Agent Patterns
Design Claude tool loops with schemas, observations, and approvals.
- Google ADK and Gemini Tool Calling
Use Gemini function calling and ADK-style orchestration patterns.
- Semantic Kernel Overview
Understand planners, functions, and enterprise orchestration in Semantic Kernel.
- LangChain for Agent Apps
Use LangChain components without hiding your product logic.
- LlamaIndex Agents and Workflows
Use LlamaIndex when data, retrieval, and agent workflows meet.
- OpenAI Agents SDK
Build provider-native agents with tools, handoffs, guardrails, and tracing.
- LangChain vs LangGraph: Which to Use When
LangChain is the right default for most LLM applications — chains, RAG, and simple agents — while LangGraph is the right choice when your control flow itself is the product: branching, resuming, interrupts, and explicit state transitions.
- Choosing an Agent Framework
Pick a framework by state, tools, durability, deployment, and team fit.
- LangGraph in Depth
Model agent workflows as state graphs with checkpoints and explicit control flow.
- CrewAI and Role-based Agents
Evaluate role-based multi-agent workflows and their tradeoffs.
Generative
- Text-to-Speech and Audio Generation
Use generated audio responsibly for narration, accessibility, and media lessons.
- Image Generation Workflows
Compare text-to-image, image-to-image, inpainting, and control workflows.
- Multimodal Prompting
Write prompts that combine text, images, audio, and structured outputs.
- Responsible Generative Media
Label, review, and govern synthetic images, speech, video, and music.
- Speech Recognition with Whisper
Transcribe audio into text for lessons, search, and agent workflows.
- Video Generation Concepts
Understand temporal coherence, prompts, and product caveats for generated video.
- Diffusion Models Explained
Learn how iterative denoising turns noise into images and other media.
- Vision-Language Models
Connect images and text for diagrams, screenshots, and multimodal tutoring.
- Hugging Face Diffusers
Use pipelines, schedulers, and adapters for diffusion workflows.
- Stable Diffusion and Latent Diffusion
Understand why running diffusion in latent space made image generation practical.
Infrastructure
- GPUs, TPUs, and AI Hardware
Understand accelerator tradeoffs for training, inference, and cost planning.
- Local Models with Ollama
Use local model serving for demos, privacy-sensitive prototypes, and dev loops.
- Model Registries and Versioning
Track models, prompts, retrieval indexes, and eval sets as release artifacts.
- Cost and Latency Optimization
Control token, retrieval, tool, and serving costs without gutting quality.
- Deployment Patterns for AI Apps
Choose hosted APIs, self-hosted models, routers, and async jobs deliberately.
- Hugging Face Transformers in Production
Use Transformers for models while knowing when to switch to serving runtimes.
- Model Gateways with LiteLLM
Route across providers with fallback, budgets, and unified interfaces.
- Monitoring Model Drift and Quality
Detect quality shifts from model, prompt, retrieval, and data changes.
- Serving LLMs with vLLM
Run open-weight models behind an OpenAI-compatible high-throughput server.
- Embedding Pipelines at Scale
Batch, version, backfill, and monitor embeddings for RAG systems.
LLMs
- Prompt Engineering Foundations
Design prompts as testable interfaces, not magic wording.
- Structured Outputs with JSON Schema
Make model responses parseable, validated, and app-safe.
- Tokenization and Context Windows
See how text becomes tokens and why context is a scarce design budget.
- Fine-tuning vs RAG vs Prompting
Choose the right adaptation lever for instructions, knowledge, or behavior.
- Pretraining and Scaling Laws
Understand why data, parameters, and compute changed model capability.
- Function Calling and Tool Use
Connect models to APIs through typed tool calls and controlled execution.
- Quantization, Distillation, and Inference Optimization
Shrink latency and cost without losing the behavior your product needs.
- RLHF, DPO, and Preference Tuning
Understand how feedback and preferences steer model behavior after pretraining.
- Transformer Attention Explained
Learn queries, keys, values, heads, and why attention scaled language models.
- How Large Language Models Work
Trace token prediction, context, sampling, and why fluent text can still be wrong.
RAG
- Chunking Strategies for RAG
Split documents so retrieval finds the exact evidence an answer needs.
- Embeddings and Vector Search
Turn questions and documents into searchable geometry.
- Reranking for Better Answers
Use cross-encoders and second-stage scoring to improve context quality.
- Hybrid Retrieval and RRF
Combine vector meaning with keyword exactness using reciprocal rank fusion.
- pgvector for RAG
Use Postgres-native vector search for grounded AI apps.
- RAG Evaluation and Faithfulness
Measure retrieval, grounding, and answer quality separately.
- What is RAG?
Learn the open-book pattern for grounding model answers in retrieved sources.
- Graph RAG
Use entities and relationships when chunk search is not enough.
- LlamaIndex for RAG
Build document loaders, indexes, retrievers, and query engines with LlamaIndex.
- Pinecone Vector Database: Complete Tutorial
Build and deploy a vector search application with Pinecone by mastering index creation, embedding ingestion, similarity querying, metadata filtering, and RAG pipeline integration.
- Vector Databases Compared
Choose between pgvector, Qdrant, Milvus, Weaviate, Chroma, and LanceDB.
Safety
- Bias and Fairness
Measure uneven behavior across groups, languages, and contexts.
- EU AI Act Basics
Understand risk-based AI obligations and why education use cases need care.
- Hallucinations and Grounding
Reduce unsupported claims with retrieval, citations, validation, and uncertainty.
- Guardrails and Validators
Layer schemas, policy checks, citation validation, and review workflows.
- Privacy and Data Governance
Minimize sensitive data in prompts, retrieval, logs, and traces.
- Safety Release Checklist
Ship AI features with documented risks, evals, monitoring, and owners.
- NIST AI RMF for GenAI
Use Govern, Map, Measure, and Manage to organize GenAI risk.
- OWASP LLM Top 10
Map LLM app threats to concrete product controls.
- Securing Tool-Using Agents
Constrain permissions, approvals, and tool outputs for agent systems.
- Prompt Injection Defense
Treat user and retrieved text as untrusted input around privileged instructions.