Compile Ready
Learning/Generative AI

Generative AI

One place to master Generative AI — a structured, ten-level roadmap from AI foundations and working with LLMs, through RAG, vector databases, and agents, into AI system design (ChatGPT, coding assistants, answer engines), production AI, and advanced topics, and finishing with interview preparation and hands-on projects. Every lesson is a full deep dive: theory, interactive diagrams, request flow, production considerations, an interview perspective, and hands-on examples.

101

Lessons

23

Available now

10

Roadmap levels

10+

Companies

13 topics across 10 levels · new lessons added regularly
Difficulty
Topic
Company

Level 1 · AI Foundations

The mental models every AI interview assumes you already have — transformers, attention, tokenization, inference, and decoding.

9/9 available
Beginner

Transformer Architecture

How the transformer block works end-to-end — embeddings, self-attention, feed-forward layers, and residual streams.

LLM FundamentalsOpenAIGoogle DeepMindMeta
40m Very High 90
Intermediate

Attention Mechanism

Scaled dot-product and multi-head attention — the intuition, the math, and why it scales to long context.

LLM FundamentalsOpenAIGoogle DeepMindNVIDIA
40m High 86
Beginner

Tokenization & Embeddings

BPE, subword vocabularies, and how tokens become vectors — the input side of every LLM.

LLM FundamentalsEmbeddingsOpenAICohereMeta
35m High 82
Intermediate

How LLM Inference Works

Prefill vs decode, the KV cache, and why the first token is slow but the rest are fast.

LLM FundamentalsModel ServingOpenAINVIDIADatabricks
40m High 84
Intermediate

Sampling & Decoding Strategies

Temperature, top-k, top-p, and beam search — how token probabilities become text, and when to use each.

LLM FundamentalsPrompt EngineeringOpenAIAnthropicCohere
35m Medium 78
Advanced

Context Windows & KV Cache

Why context is expensive, how the KV cache grows, and the tricks that push context from 4K to 1M tokens.

LLM FundamentalsModel ServingAnthropicGoogle DeepMindNVIDIA
40m Medium 80
Intermediate

Hallucinations & LLM Limitations

Why LLMs make things up, how to measure it, and the system-level mitigations interviewers expect you to know.

LLM FundamentalsAI EvaluationAnthropicOpenAIMicrosoft
35m Medium 79
Beginner

Prompt Engineering Foundations

System vs user prompts, few-shot, chain-of-thought, and structured output — the reliable building blocks.

Prompt EngineeringLLM FundamentalsOpenAIAnthropicMicrosoft
35m High 83
Intermediate

Choosing the Right Model

Open vs closed, size vs latency vs cost, and how to pick a model (or a cascade) for a given workload.

LLM FundamentalsModel ServingDatabricksMicrosoftAmazon
35m Medium 76

Level 2 · Working with LLMs

Building on model APIs day to day — provider SDKs, structured outputs, JSON mode, streaming, function/tool calling, prompt templates, and guardrails.

11/11 available
Beginner

Calling the OpenAI API

The Chat Completions and Responses APIs end-to-end — messages, roles, parameters, token accounting, and error handling.

LLM FundamentalsPrompt EngineeringOpenAIMicrosoft
35m High 88
Beginner

Calling the Anthropic (Claude) API

Claude's Messages API — system prompts, content blocks, stop reasons, and prompt-caching for cheaper long context.

LLM FundamentalsPrompt EngineeringAnthropic
35m High 84
Beginner

Calling the Google Gemini API

Gemini's generateContent API — multimodal inputs, safety settings, and grounding with Google Search.

LLM FundamentalsPrompt EngineeringGoogle DeepMind
35m Medium 80
Intermediate

Azure OpenAI Service

Running OpenAI models on Azure — deployments, regional data residency, private networking, and enterprise auth.

LLM FundamentalsAI InfrastructureMicrosoftOpenAI
35m Medium 78
Intermediate

Structured Outputs

Guaranteeing schema-valid responses — JSON Schema, response formats, and refusal handling for reliable pipelines.

Prompt EngineeringAI EvaluationOpenAIAnthropic
35m High 85
Beginner

JSON Mode

Forcing valid JSON from any model — when to use JSON mode vs structured outputs, and how to recover from partial output.

Prompt EngineeringOpenAIAnthropicGoogle DeepMind
30m Medium 79
Intermediate

Streaming Responses

Server-sent events and token streaming — delta parsing, backpressure, cancellation, and rendering partial tokens in the UI.

LLM FundamentalsModel ServingOpenAIAnthropic
35m High 83
Intermediate

Function & Tool Calling

Letting the model call your code — tool schemas, argument validation, parallel tool calls, and the tool-result loop.

AI AgentsPrompt EngineeringOpenAIAnthropicGoogle DeepMind
40m Very High 89
Intermediate

Model Context Protocol (MCP)

The open standard for connecting models to tools and data — servers, resources, tools, and transport, and why it matters.

AI AgentsAI InfrastructureAnthropicOpenAI
40m Medium 81
Intermediate

Prompt Templates & Chaining

Reusable, versioned prompts and multi-step chains — variables, few-shot templates, and composing calls into workflows.

Prompt EngineeringOpenAIDatabricks
35m Medium 77
Intermediate

Output Guardrails & Validation

Keeping model output safe and correct — content filters, schema validation, retries, and fallbacks before you trust a response.

AI SecurityAI EvaluationOpenAIAnthropicMicrosoft
40m High 82

Level 3 · Retrieval-Augmented Generation

Grounding LLMs in your own data — chunking, hybrid retrieval, reranking, evaluation, and cost control.

1/8 available
Advanced

Design a Production RAG System

Design an end-to-end retrieval-augmented generation system — ingestion, chunking, embedding, hybrid retrieval, reranking, and grounded generation at scale.

RAGVector DatabasesOpenAIDatabricksCohere
55m Very High 98
Intermediate Coming soon

Document Chunking Strategies

Fixed, recursive, semantic, and structure-aware chunking — how splitting decisions make or break retrieval quality.

RAGEmbeddingsCohereDatabricksMicrosoft
40m High 82
Advanced Coming soon

Hybrid Search for RAG

Combine BM25 keyword search with dense vectors and fuse the results — the retrieval backbone of strong RAG.

RAGVector DatabasesCohereMicrosoftDatabricks
45m High 84
Intermediate Coming soon

Reranking in RAG Pipelines

Cross-encoder rerankers — why a second stage dramatically lifts precision, and how to keep it cheap.

RAGAI EvaluationCohereOpenAIGoogle DeepMind
40m Medium 80
Advanced Coming soon

Evaluating RAG Quality

Retrieval and generation metrics — recall@k, faithfulness, answer relevance, and LLM-as-judge pipelines.

AI EvaluationRAGDatabricksAnthropicMicrosoft
45m High 81
Advanced Coming soon

Multimodal RAG

Retrieve over text, tables, and images — unified embeddings, layout parsing, and grounded multimodal answers.

RAGEmbeddingsGoogle DeepMindOpenAICohere
45m Medium 73
Advanced Coming soon

Agentic RAG

Let the model decide when and what to retrieve — query planning, multi-hop retrieval, and self-correction.

RAGAI AgentsAnthropicOpenAIPerplexity
50m Medium 79
Intermediate Coming soon

Cost & Caching for RAG

Semantic caching, embedding reuse, and context trimming — how to cut RAG bills without hurting quality.

RAGAI ObservabilityDatabricksAmazonMicrosoft
40m Medium 75

Level 4 · Vector Databases & Search

The retrieval substrate behind RAG — embeddings, ANN indexes (HNSW, IVF-PQ), sharding, and filtered search at billion scale.

1/8 available
Advanced

Design a Vector Database

Design a vector database that indexes billions of embeddings for millisecond similarity search — ANN indexing, sharding, filtering, and persistence.

Vector DatabasesEmbeddingsDatabricksNVIDIAMicrosoft
55m Very High 95
Advanced Coming soon

Approximate Nearest Neighbor Algorithms

The ANN landscape — trees, LSH, graphs, and quantization — and the recall/latency/memory tradeoffs between them.

Vector DatabasesNVIDIAGoogle DeepMindDatabricks
45m High 83
Advanced Coming soon

HNSW Index Deep Dive

Hierarchical navigable small worlds — how the graph is built and searched, and how to tune ef and M.

Vector DatabasesNVIDIADatabricksCohere
45m Medium 81
Advanced Coming soon

IVF & Product Quantization

Inverted-file indexing and PQ compression — the technique that makes billion-vector search fit in RAM.

Vector DatabasesEmbeddingsMetaNVIDIADatabricks
45m Medium 74
Advanced Coming soon

Storing Billions of Embeddings

Memory vs disk (DiskANN), tiered storage, and the cost model behind large-scale vector storage.

Vector DatabasesAI InfrastructureMicrosoftAmazonDatabricks
45m Medium 72
Advanced Coming soon

Sharding & Replication for Vector DBs

Partition billions of vectors across nodes, replicate for availability, and scatter-gather queries with low tail latency.

Vector DatabasesAI InfrastructureDatabricksAmazonNVIDIA
50m Medium 76
Advanced Coming soon

Filtered Vector Search

Combine metadata predicates with similarity — pre-, post-, and single-stage filtering, and why it is surprisingly hard.

Vector DatabasesMicrosoftCohereDatabricks
40m Medium 70
Intermediate Coming soon

Choosing an Embedding Model

Dimensionality, domain fit, MTEB benchmarks, and cost — how to pick and evaluate an embedding model.

EmbeddingsAI EvaluationCohereOpenAIDatabricks
35m Medium 71

Level 5 · AI Agents & Orchestration

Systems that plan and act — tool calling, memory, guardrails, and multi-agent orchestration.

0/8 available
Advanced Coming soon

Design an AI Agent

Design a single tool-using agent — the reasoning loop, tool schema, memory, and error recovery.

AI AgentsPrompt EngineeringAnthropicOpenAIMicrosoft
55m Very High 90
Intermediate Coming soon

Tool Calling & Function Calling

How models call functions — schema design, argument validation, parallel calls, and safe execution.

AI AgentsPrompt EngineeringOpenAIAnthropicGoogle DeepMind
40m High 86
Advanced Coming soon

Agent Memory Systems

Short-term, long-term, and episodic memory — summarization, vector recall, and context management for agents.

AI AgentsRAGAnthropicOpenAIMicrosoft
45m High 80
Advanced Coming soon

ReAct & Planning Loops

Reason-act-observe loops, plan-and-execute, and reflection — the control structures behind capable agents.

AI AgentsGoogle DeepMindAnthropicOpenAI
45m Medium 78
Advanced Coming soon

Design an Autonomous Task Agent

Design a long-running agent that decomposes goals, runs tools, and checkpoints progress with human approval gates.

AI AgentsAI SecurityOpenAIAnthropicAmazon
55m Medium 77
Advanced Coming soon

Agent Guardrails & Safety

Sandboxing tools, permission scopes, and output validation — keeping autonomous agents from doing damage.

AI SecurityAI AgentsAnthropicMicrosoftOpenAI
45m Medium 75
Advanced Coming soon

Design a Multi-Agent System

Design an orchestrator-worker multi-agent system — role decomposition, shared state, and conflict resolution.

Multi-Agent SystemsAI AgentsMicrosoftOpenAIGoogle DeepMind
55m High 82
Advanced Coming soon

Design a Web-Browsing Agent

Design an agent that navigates real web pages — DOM grounding, action space, safety, and rate limiting.

AI AgentsAI SecurityOpenAIAnthropicGoogle DeepMind
55m Medium 74

Level 6 · AI System Design

End-to-end product systems built on top of LLMs — ChatGPT, coding assistants, answer engines, content moderation, and streaming UX.

1/8 available
Advanced

Design ChatGPT

Design a multi-turn conversational AI product — streaming responses, conversation memory, moderation, and scale to millions of users.

Model ServingPrompt EngineeringOpenAIMicrosoftAnthropic
55m Very High 99
Advanced Coming soon

Design an AI Coding Assistant

Design a Copilot-style assistant — repo context, fill-in-the-middle completion, low latency, and privacy.

Model ServingRAGMicrosoftOpenAIAmazon
55m High 92
Intermediate Coming soon

Design an AI Customer Support System

Design an LLM support agent grounded in help-center docs with escalation, tools, and deflection metrics.

RAGAI AgentsAmazonMicrosoftAnthropic
50m High 85
Intermediate Coming soon

Design an AI Writing Assistant

Design a Grammarly/Notion-AI-style assistant — inline suggestions, tone control, and multi-tenant data isolation.

Prompt EngineeringModel ServingMicrosoftGoogle DeepMindOpenAI
45m Medium 78
Advanced Coming soon

Design a Multi-User LLM Chat Platform

Design the backend for a team chat product with shared threads, per-user quotas, and provider fallback.

Model ServingAI ObservabilityOpenAIMicrosoftDatabricks
50m Medium 76
Advanced Coming soon

Design an AI Answer Engine

Design a Perplexity-style answer engine — live web retrieval, citation grounding, and streamed synthesis.

RAGAI AgentsPerplexityGoogle DeepMindMicrosoft
55m High 88
Intermediate Coming soon

Design an LLM Content Moderation System

Design a real-time safety classifier pipeline — policy taxonomy, latency budget, and human review loop.

AI SecurityAI EvaluationMetaOpenAIMicrosoft
45m Medium 74
Intermediate Coming soon

Design Streaming Token Delivery

Design the transport for token-by-token responses — SSE vs WebSockets, backpressure, and cancellation.

Model ServingOpenAIAnthropicAmazon
40m Medium 72

Level 7 · Production AI

Running AI in production — model serving, KV cache, batching, quantization, observability, evaluation, semantic caching, and cost optimization.

0/16 available
Advanced Coming soon

Design an LLM Inference Service

Design a high-throughput inference service — request queue, batching, KV cache, GPU pooling, and autoscaling.

Model ServingAI InfrastructureNVIDIAOpenAIDatabricks
55m Very High 93
Advanced Coming soon

KV Cache Optimization

PagedAttention, cache eviction, and prefix sharing — the memory tricks that multiply inference throughput.

Model ServingNVIDIAOpenAIAnthropic
40m High 82
Advanced Coming soon

Continuous Batching

Iteration-level scheduling that keeps GPUs saturated — why it beats static batching for LLM serving.

Model ServingNVIDIADatabricksOpenAI
40m Medium 80
Advanced Coming soon

Speculative Decoding

Draft-and-verify decoding — use a small model to propose tokens a big model checks, cutting latency.

Model ServingNVIDIAGoogle DeepMindAnthropic
40m Medium 76
Advanced Coming soon

GPU Scheduling & Autoscaling

Bin-packing GPUs, cold-start mitigation, and scaling on queue depth — the ops side of inference at scale.

Model ServingAI InfrastructureAmazonNVIDIADatabricks
45m Medium 78
Advanced Coming soon

Quantization for Inference

INT8, FP8, and 4-bit weights — how quantization shrinks models and the accuracy tradeoffs to defend.

Model ServingFine-TuningNVIDIAMetaDatabricks
40m Medium 75
Advanced Coming soon

Multi-Model & LoRA Serving

Serve hundreds of fine-tuned adapters from one base model — LoRA swapping, routing, and memory sharing.

Model ServingFine-TuningDatabricksNVIDIAAmazon
45m Medium 73
Intermediate Coming soon

Design an LLM Gateway

Design a unified gateway across providers — routing, rate limits, key management, caching, and fallbacks.

Model ServingAI ObservabilityMicrosoftAmazonDatabricks
45m High 79
Advanced Coming soon

Design LLM Observability

Design tracing for LLM apps — spans across retrieval and generation, token/cost metrics, and quality signals.

AI ObservabilityAI EvaluationDatabricksMicrosoftAmazon
50m High 82
Advanced Coming soon

Design an LLM Evaluation Platform

Design an offline+online eval platform — golden sets, LLM-as-judge, human review, and regression gates.

AI EvaluationAI ObservabilityOpenAIDatabricksAnthropic
50m High 80
Intermediate Coming soon

A/B Testing LLM Features

Experiment on prompts and models — metrics, guardrail metrics, and why LLM experiments are noisy.

AI EvaluationAI ObservabilityMetaMicrosoftAmazon
40m Medium 73
Intermediate Coming soon

LLM Cost Optimization

Model cascades, caching, batching, and prompt compression — a systematic playbook for cutting inference cost.

AI ObservabilityModel ServingDatabricksAmazonMicrosoft
40m High 81
Intermediate Coming soon

Design a Prompt Management System

Design versioned prompt storage — templates, variables, staged rollout, and rollback tied to evals.

Prompt EngineeringAI ObservabilityMicrosoftDatabricksOpenAI
40m Medium 74
Advanced Coming soon

Design a Semantic Cache

Design an embedding-based cache for LLM responses — similarity thresholds, staleness, and correctness risks.

AI ObservabilityVector DatabasesDatabricksAmazonCohere
45m Medium 75
Advanced Coming soon

Model Monitoring & Drift Detection

Detect data and quality drift in production — distribution monitors, canaries, and automated rollback.

AI ObservabilityAI EvaluationDatabricksAmazonMicrosoft
40m Medium 72
Advanced Coming soon

Design an LLMOps CI/CD Pipeline

Design CI/CD for prompts, models, and RAG indexes — eval gates, staged rollout, and automated rollback.

AI ObservabilityAI InfrastructureDatabricksMicrosoftAmazon
50m Medium 76

Level 8 · Advanced AI

The platforms and hard problems behind the models — distributed training, fine-tuning, RLHF, feature stores, safety, security, and governance.

0/16 available
Advanced Coming soon

Design a Distributed Training Platform

Design a platform to train large models — job scheduling, data/model/pipeline parallelism, and checkpointing.

AI InfrastructureFine-TuningNVIDIAGoogle DeepMindMeta
55m High 84
Advanced Coming soon

Design an LLM Data Pipeline

Design a pretraining/fine-tuning data pipeline — crawling, dedup, filtering, tokenization, and lineage.

AI InfrastructureFine-TuningMetaDatabricksGoogle DeepMind
50m Medium 78
Advanced Coming soon

Distributed Training Strategies

Data, tensor, pipeline, and FSDP parallelism — how huge models are split across thousands of GPUs.

AI InfrastructureNVIDIAMetaGoogle DeepMind
50m Medium 76
Advanced Coming soon

Design a Feature Store

Design online/offline feature storage — consistency, point-in-time correctness, and low-latency serving.

AI InfrastructureDatabricksAmazonMeta
50m Medium 72
Intermediate Coming soon

Experiment Tracking & Model Registry

Track runs, version datasets and models, and gate promotions — the reproducibility backbone of ML.

AI InfrastructureAI ObservabilityDatabricksMicrosoftAmazon
40m Medium 70
Advanced Coming soon

Design a Fine-Tuning Pipeline

Design a pipeline for supervised fine-tuning and LoRA — data curation, training, eval gates, and rollout.

Fine-TuningAI InfrastructureDatabricksOpenAIMeta
50m Medium 77
Advanced Coming soon

Design an RLHF Pipeline

Design reinforcement learning from human feedback — preference data, reward modeling, and PPO/DPO training.

Fine-TuningAI InfrastructureOpenAIAnthropicGoogle DeepMind
55m Medium 79
Advanced Coming soon

GPU Cluster Management

Fair-share scheduling, gang scheduling, and fault recovery for large GPU clusters running mixed workloads.

AI InfrastructureNVIDIAMetaAmazon
45m Low 71
Advanced Coming soon

Defending Against Prompt Injection

Direct and indirect prompt injection — the threat model, and layered defenses interviewers want to hear.

AI SecurityAI AgentsAnthropicMicrosoftOpenAI
45m High 85
Advanced Coming soon

Design an LLM Guardrail System

Design input/output guardrails — policy checks, schema validation, PII filters, and safe-completion routing.

AI SecurityAI EvaluationMicrosoftOpenAIAnthropic
50m High 80
Intermediate Coming soon

PII Detection & Redaction

Detect and redact sensitive data before it reaches a model — classifiers, tokenization, and reversible masking.

AI SecurityMicrosoftAmazonDatabricks
40m Medium 73
Advanced Coming soon

Hallucination Mitigation

System-level mitigations — grounding, citations, self-consistency, and abstention — with measurable guarantees.

AI EvaluationRAGAnthropicGoogle DeepMindOpenAI
45m Medium 76
Advanced Coming soon

Design an AI Content Safety Pipeline

Design a safety pipeline for generated text and images — classifiers, thresholds, appeals, and audit trails.

AI SecurityAI EvaluationMetaMicrosoftOpenAI
50m Medium 72
Intermediate Coming soon

Model Access Control & Rate Limiting

Per-tenant quotas, token budgets, and abuse detection — protecting expensive model endpoints.

AI SecurityModel ServingOpenAIAmazonMicrosoft
40m Medium 71
Intermediate Coming soon

AI Governance & Audit Logging

Model cards, data lineage, approval workflows, and immutable audit logs — the compliance layer for AI.

AI SecurityAI ObservabilityMicrosoftDatabricksAmazon
40m Low 68
Advanced Coming soon

Jailbreak Detection

Detect adversarial prompts that bypass safety — classifiers, canaries, and red-teaming feedback loops.

AI SecurityAI EvaluationAnthropicOpenAIGoogle DeepMind
40m Medium 70

Level 9 · Interview Preparation

Full mock-interview problems that combine everything — recommendations, image generation, voice, translation, and more.

0/9 available
Advanced Coming soon

Design AI-Powered Recommendations

Design a recommendation system with embeddings and LLM re-ranking — candidate generation, ranking, and freshness.

EmbeddingsVector DatabasesMetaAmazonGoogle DeepMind
55m High 84
Advanced Coming soon

Design an Image Generation Service

Design a text-to-image service — diffusion inference, GPU queueing, safety filters, and asset storage.

Model ServingAI InfrastructureOpenAINVIDIAGoogle DeepMind
55m High 80
Advanced Coming soon

Design a Voice Assistant

Design a real-time voice assistant — streaming ASR, LLM reasoning, TTS, and end-to-end latency budgets.

Model ServingAI AgentsAmazonGoogle DeepMindOpenAI
55m Medium 78
Advanced Coming soon

Design an AI Code Review System

Design an AI reviewer for pull requests — repo context, diff analysis, false-positive control, and CI integration.

RAGAI AgentsMicrosoftOpenAIAmazon
55m Medium 77
Advanced Coming soon

Design an AI Fraud Detection System

Design a hybrid ML + LLM fraud system — features, real-time scoring, explanations, and analyst tooling.

AI InfrastructureModel ServingAmazonMicrosoftMeta
55m Medium 74
Intermediate Coming soon

Design an AI Meeting Notetaker

Design a meeting assistant — diarized transcription, summarization, action items, and searchable history.

Model ServingRAGMicrosoftGoogle DeepMindAmazon
50m Medium 73
Advanced Coming soon

Design Real-Time AI Translation

Design streaming speech-to-speech translation — incremental decoding, latency, and quality/latency tradeoffs.

Model ServingMetaGoogle DeepMindMicrosoft
50m Medium 71
Intermediate Coming soon

Design an AI Tutor

Design a personalized tutoring system — knowledge modeling, adaptive prompts, grounding, and safety for minors.

RAGPrompt EngineeringMicrosoftOpenAIGoogle DeepMind
50m Medium 70
Advanced Coming soon

Design an LLM Personalization Engine

Design a system that personalizes LLM outputs per user — profile memory, retrieval, and privacy controls.

RAGEmbeddingsMetaAmazonMicrosoft
55m Medium 72

Level 10 · Hands-On Projects

Capstone builds that turn the roadmap into portfolio projects — build ChatGPT, a coding copilot, a RAG system, an agent, and an AI search engine.

0/8 available
Intermediate Coming soon

Build ChatGPT from Scratch

A capstone build of a streaming chat app — conversation state, streaming responses, message history, and persistence.

LLM FundamentalsModel ServingOpenAI
90m Medium 86
Advanced Coming soon

Build an AI Coding Copilot

A capstone build of an inline code assistant — repo context, fill-in-the-middle, tool calling, and diff application.

RAGAI AgentsMicrosoftOpenAI
120m Medium 84
Intermediate Coming soon

Build a RAG System

A capstone build of an end-to-end RAG app — ingestion, chunking, embeddings, a vector store, retrieval, and grounded answers.

RAGVector DatabasesCohereDatabricks
120m Medium 85
Advanced Coming soon

Build an AI Agent

A capstone build of a tool-using agent — planning loop, tool execution, memory, and guardrails against runaway loops.

AI AgentsMulti-Agent SystemsAnthropicOpenAI
120m Medium 83
Advanced Coming soon

Build an AI Coding Assistant

A capstone build of a chat-based coding assistant — codebase indexing, retrieval over source, and multi-file edits.

RAGAI AgentsMicrosoftOpenAI
120m Medium 80
Advanced Coming soon

Build an AI Search Engine

A capstone build of an answer engine — query understanding, retrieval, reranking, cited synthesis, and follow-ups.

RAGVector DatabasesPerplexityOpenAI
120m Medium 82
Advanced Coming soon

Build an AI Workflow Platform

A capstone build of a node-based workflow runner — chaining prompts and tools, branching, retries, and observability.

AI AgentsAI ObservabilityDatabricksMicrosoft
120m Medium 76
Intermediate Coming soon

Build a Document Chat App

A capstone build of chat-with-your-PDF — upload, parsing, chunking, retrieval, and grounded answers with citations.

RAGVector DatabasesCohereOpenAI
90m Medium 81