← Courses Catalogue

AI Engineering from Scratch

▸ Setup And Tooling

▸ Dev Environment

▸ Code

{ }Main { }Verify { }Verify

▸ Docs

MDev Environment

▸ Outputs

MPrompt Env Check

▸ Git And Collaboration

▸ Docs

MGit & Collaboration

▸ Gpu Setup And Cloud

▸ Code

▸ Docs

MGPU Setup & Cloud

▸ Apis And Keys

▸ Code

{ }First Api Call { }First Api Call

▸ Docs

▸ Outputs

MPrompt Api Troubleshooter

▸ Jupyter Notebooks

▸ Code

{ }Notebook Tips

▸ Docs

MJupyter Notebooks

▸ Outputs

MPrompt Notebook Helper

▸ Python Environments

▸ Code

▸ Docs

MPython Environments

▸ Docker For Ai

▸ Code

{ }Docker Compose { }Dockerfile

▸ Docs

▸ Editor Setup

▸ Code

▸ Vscode

{ }Extensions { }Settings

▸ Docs

▸ Data Management

▸ Code

▸ Docs

MData Management

▸ Outputs

MPrompt Data Helper

▸ Terminal And Shell

▸ Code

{ }Shell Aliases

▸ Docs

MTerminal & Shell

▸ Linux For Ai

▸ Docs

▸ Debugging And Profiling

▸ Code

▸ Docs

MDebugging and Profiling

▸ Outputs

MPrompt Debug Ai Code

▸ Math Foundations

▸ Linear Algebra Intuition

▸ Code

▸ Docs

MLinear Algebra Intuition

▸ Outputs

MPrompt Linear Algebra Tutor

▸ Vectors Matrices Operations

▸ Code

▸ Docs

MVectors, Matrices & Operations

▸ Outputs

MPrompt Matrix Operations

▸ Matrix Transformations

▸ Code

{ }Transformations

▸ Docs

MMatrix Transformations

▸ Outputs

MPrompt Transformation Visualizer

▸ Calculus For Ml

▸ Code

▸ Docs

MCalculus for Machine Learning

▸ Outputs

MGradient Computation for ML

▸ Chain Rule And Autodiff

▸ Code

▸ Docs

MChain Rule & Automatic Differentiation

▸ Outputs

MSkill Autodiff

▸ Probability And Distributions

▸ Code

▸ Docs

MProbability and Distributions

▸ Outputs

MProbability Distribution Selection

▸ Bayes Theorem

▸ Code

▸ Docs

MBayes' Theorem

▸ Outputs

MPrompt Bayesian Reasoning

▸ Optimization

▸ Code

▸ Docs

▸ Outputs

MPrompt Optimizer Guide

▸ Information Theory

▸ Code

{ }Information Theory

▸ Docs

MInformation Theory

▸ Outputs

MInformation Theory for ML

▸ Dimensionality Reduction

▸ Code

{ }Dim Reduction

▸ Docs

MDimensionality Reduction

▸ Outputs

MSkill Dimensionality Reduction

▸ Singular Value Decomposition

▸ Code

▸ Docs

MSingular Value Decomposition

▸ Outputs

▸ Tensor Operations

▸ Code

▸ Docs

MTensor Operations

▸ Outputs

MPrompt Tensor Debugger MPrompt Tensor Shapes

▸ Numerical Stability

▸ Code

▸ Docs

MNumerical Stability

▸ Outputs

▸ Norms And Distances

▸ Code

▸ Docs

MNorms and Distances

▸ Outputs

MPrompt Distance Chooser

▸ Statistics For Ml

▸ Code

▸ Docs

MStatistics for Machine Learning

▸ Outputs

MStatistical Testing for ML

▸ Sampling Methods

▸ Code

▸ Docs

MSampling Methods

▸ Outputs

MSampling Strategy Selection

▸ Linear Systems

▸ Code

{ }Linear Systems

▸ Docs

MLinear Systems

▸ Outputs

MPrompt Linear Solver

▸ Convex Optimization

▸ Code

▸ Docs

MConvex Optimization

▸ Outputs

MConvexity Checker

▸ Complex Numbers

▸ Code

{ }Complex Numbers

▸ Docs

MComplex Numbers for AI

▸ Outputs

MSkill Complex Arithmetic

▸ Fourier Transform

▸ Code

▸ Docs

MThe Fourier Transform

▸ Outputs

MPrompt Spectral Analyzer

▸ Graph Theory

▸ Code

{ }Graph Theory

▸ Docs

MGraph Theory for Machine Learning

▸ Outputs

MSkill Graph Analysis

▸ Stochastic Processes

▸ Code

▸ Docs

MStochastic Processes

▸ Outputs

MPrompt Stochastic Process Advisor

▸ Ml Fundamentals

▸ What Is Machine Learning

▸ Code

▸ Docs

MWhat Is Machine Learning

▸ Outputs

MPrompt Ml Problem Framer

▸ Linear Regression

▸ Code

{ }Linear Regression

▸ Docs

MLinear Regression

▸ Outputs

MRegression Strategy Guide

▸ Logistic Regression

▸ Code

{ }Logistic Regression

▸ Docs

MLogistic Regression

▸ Outputs

MClassification Baseline Guide

▸ Decision Trees

▸ Code

▸ Docs

MDecision Trees and Random Forests

▸ Outputs

MPrompt Tree Interpreter

▸ Support Vector Machines

▸ Code

▸ Docs

MSupport Vector Machines

▸ Outputs

MSVM Kernel Selection Guide

▸ Knn And Distances

▸ Code

▸ Docs

MK-Nearest Neighbors and Distances

▸ Outputs

MPrompt Distance Metric Advisor

▸ Unsupervised Learning

▸ Code

▸ Docs

MUnsupervised Learning

▸ Outputs

MClustering Algorithm Selection Guide

▸ Feature Engineering

▸ Code

▸ Docs

MFeature Engineering & Selection

▸ Outputs

MFeature Engineering Prompt

▸ Model Evaluation

▸ Code

▸ Docs

MModel Evaluation

▸ Outputs

MModel Evaluation Strategy

▸ Bias Variance

▸ Code

{ }Bias Variance

▸ Docs

MBias-Variance Tradeoff

▸ Outputs

MPrompt Model Diagnostics

▸ Ensemble Methods

▸ Code

▸ Docs

MEnsemble Methods

▸ Outputs

MPrompt Ensemble Selector MEnsemble Method Selection Guide

▸ Hyperparameter Tuning

▸ Code

▸ Docs

MHyperparameter Tuning

▸ Outputs

MPrompt Tuning Strategy

▸ Ml Pipelines

▸ Code

▸ Docs

▸ Outputs

MPrompt Ml Pipeline

▸ Naive Bayes

▸ Code

▸ Docs

▸ Outputs

MSkill Naive Bayes Chooser

▸ Time Series

▸ Code

▸ Docs

MTime Series Fundamentals

▸ Outputs

MPrompt Time Series Advisor

▸ Anomaly Detection

▸ Code

{ }Anomaly Detection

▸ Docs

MAnomaly Detection

▸ Outputs

MSkill Anomaly Detector

▸ Imbalanced Data

▸ Code

▸ Docs

MHandling Imbalanced Data

▸ Outputs

MImbalanced Data Strategy

▸ Feature Selection

▸ Code

{ }Feature Selection

▸ Docs

MFeature Selection

▸ Outputs

MFeature Selection Strategy

▸ Deep Learning Core

▸ The Perceptron

▸ Code

▸ Docs

MThe Perceptron

▸ Outputs

MThe Perceptron Pattern

▸ Multi Layer Networks

▸ Code

▸ Docs

MMulti-Layer Networks and Forward Pass

▸ Outputs

MPrompt Network Architect

▸ Backpropagation

▸ Code

▸ Docs

MBackpropagation from Scratch

▸ Outputs

MPrompt Gradient Debugger

▸ Activation Functions

▸ Code

▸ Docs

MActivation Functions

▸ Outputs

MPrompt Activation Selector

▸ Loss Functions

▸ Code

▸ Docs

MLoss Functions

▸ Outputs

MPrompt Loss Debugger MPrompt Loss Function Selector

▸ Optimizers

▸ Code

▸ Docs

▸ Outputs

MPrompt Optimizer Selector

▸ Regularization

▸ Code

▸ Docs

MRegularization

▸ Outputs

MPrompt Regularization Advisor

▸ Weight Initialization

▸ Code

▸ Docs

MWeight Initialization and Training Stability

▸ Outputs

MPrompt Init Strategy

▸ Learning Rate Schedules

▸ Code

▸ Docs

MLearning Rate Schedules and Warmup

▸ Outputs

MPrompt Lr Schedule Advisor

▸ Mini Framework

▸ Code

▸ Docs

MBuild Your Own Mini Framework

▸ Outputs

MPrompt Framework Architect

▸ Intro To Pytorch

▸ Code

{ }Pytorch Intro

▸ Docs

MIntroduction to PyTorch

▸ Outputs

MPrompt Pytorch Debugger MSkill Pytorch Patterns

▸ Intro To Jax

▸ Code

▸ Docs

MIntroduction to JAX

▸ Outputs

MPrompt Jax Optimizer MJAX Functional Patterns

▸ Debugging Neural Networks

▸ Code

{ }Debug Neural Nets

▸ Docs

MDebugging Neural Networks

▸ Outputs

MPrompt Nn Debugger MNeural Network Debug Checklist

▸ Computer Vision

▸ Image Fundamentals

▸ Code

▸ Docs

MImage Fundamentals — Pixels, Channels, Color Spaces

▸ Outputs

MPrompt Vision Preprocessing Audit MImage Tensor Inspector

▸ Convolutions From Scratch

▸ Code

▸ Docs

MConvolutions from Scratch

▸ Outputs

MPrompt Cnn Architect MConv Shape Calculator

▸ Cnns Lenet To Resnet

▸ Code

▸ Docs

MCNNs — LeNet to ResNet

▸ Outputs

MPrompt Backbone Selector MResidual Block Reviewer

▸ Image Classification

▸ Code

▸ Docs

MImage Classification

▸ Outputs

MPrompt Classifier Pipeline Auditor MClassification Diagnostics

▸ Transfer Learning

▸ Code

▸ Docs

MTransfer Learning & Fine-Tuning

▸ Outputs

MPrompt Fine Tune Planner MFreeze Inspector

▸ Object Detection Yolo

▸ Code

▸ Docs

MObject Detection — YOLO from Scratch

▸ Outputs

MPrompt Detection Metric Reader MAnchor Designer

▸ Semantic Segmentation Unet

▸ Code

▸ Docs

MSemantic Segmentation — U-Net

▸ Outputs

MPrompt Segmentation Task Picker MSegmentation Mask Inspector

▸ Instance Segmentation Mask Rcnn

▸ Code

▸ Docs

MInstance Segmentation — Mask R-CNN

▸ Outputs

MPrompt Instance Vs Semantic Router MMask R-CNN Head Swapper

▸ Image Generation Gans

▸ Code

▸ Docs

MImage Generation — GANs

▸ Outputs

MPrompt Gan Training Triage MDCGAN Scaffold

▸ Image Generation Diffusion

▸ Code

▸ Docs

MImage Generation — Diffusion Models

▸ Outputs

MPrompt Diffusion Sampler Picker MNoise Schedule Designer

▸ Stable Diffusion

▸ Code

▸ Docs

MStable Diffusion — Architecture & Fine-Tuning

▸ Outputs

MPrompt Sd Pipeline Planner MLoRA Training Setup

▸ Video Understanding

▸ Code

▸ Docs

MVideo Understanding — Temporal Modeling

▸ Outputs

MPrompt Video Architecture Picker MFrame Sampler Auditor

▸ 3d Vision Nerf

▸ Code

▸ Docs

M3D Vision — Point Clouds & NeRFs

▸ Outputs

MPrompt 3d Task Router MPoint Cloud Loader

▸ Vision Transformers

▸ Code

▸ Docs

MVision Transformers (ViT)

▸ Outputs

MPrompt Vit Vs Cnn Picker MViT Patch and Positional Embedding Inspector

▸ Real Time Edge

▸ Code

{ }Main { }Main

▸ Docs

MReal-Time Vision — Edge Deployment

▸ Outputs

MPrompt Edge Deployment Planner MLatency Profiler

▸ Vision Pipeline Capstone

▸ Code

▸ Docs

MBuild a Complete Vision Pipeline — Capstone

▸ Outputs

MPrompt Vision Service Shape Reviewer MPipeline Budget Planner

▸ Self Supervised Vision

▸ Code

▸ Docs

MSelf-Supervised Vision — SimCLR, DINO, MAE

▸ Outputs

MPrompt Ssl Pretraining Picker MLinear Probe Runner

▸ Open Vocab Clip

▸ Code

▸ Docs

MOpen-Vocabulary Vision — CLIP

▸ Outputs

MPrompt Zero Shot Class Picker MImage-Text Retriever

▸ Ocr Document Understanding

▸ Code

▸ Docs

MOCR & Document Understanding

▸ Outputs

MPrompt Ocr Stack Picker MCTC Decoder

▸ Image Retrieval Metric

▸ Code

▸ Docs

MImage Retrieval & Metric Learning

▸ Outputs

MPrompt Retrieval Loss Picker MRecall@K Runner

▸ Keypoint Pose

▸ Code

▸ Docs

MKeypoint Detection & Pose Estimation

▸ Outputs

MPrompt Pose Stack Picker MHeatmap to Coords

▸ 3d Gaussian Splatting

▸ Code

▸ Docs

M3D Gaussian Splatting from Scratch

▸ Outputs

MPrompt 3dgs Capture Planner M3DGS Export Router

▸ Diffusion Transformers Rectified Flow

▸ Code

▸ Docs

MDiffusion Transformers & Rectified Flow

▸ Outputs

MPrompt Dit Model Picker MRectified Flow Trainer

▸ Sam3 Open Vocab Segmentation

▸ Code

▸ Docs

MSAM 3 & Open-Vocabulary Segmentation

▸ Outputs

MPrompt Open Vocab Stack Picker MConcept Prompt Designer

▸ Vision Language Models

▸ Code

▸ Docs

MVision-Language Models — The ViT-MLP-LLM Pattern

▸ Outputs

MPrompt Vlm Selector MCMER Monitor

▸ Monocular Depth

▸ Code

▸ Docs

MMonocular Depth & Geometry Estimation

▸ Outputs

MPrompt Depth Model Picker MDepth to Point Cloud

▸ Multi Object Tracking

▸ Code

▸ Docs

MMulti-Object Tracking & Video Memory

▸ Outputs

MPrompt Tracker Picker MMOT Evaluator

▸ World Models Video Diffusion

▸ Code

▸ Docs

MWorld Models & Video Diffusion

▸ Outputs

MPrompt Video Model Picker MPhysical Plausibility Checks

▸ Nlp Foundations To Advanced

▸ Text Processing

▸ Assets

▸ Code

▸ Docs

MText Processing — Tokenization, Stemming, Lemmatization

▸ Outputs

MPrompt Preprocessing Advisor

▸ Bag Of Words Tfidf

▸ Assets

▸ Code

▸ Docs

MBag of Words, TF-IDF, and Text Representation

▸ Outputs

MPrompt Vectorization Picker

▸ Word Embeddings Word2vec

▸ Assets

▸ Code

▸ Docs

MWord Embeddings — Word2Vec from Scratch

▸ Outputs

MSkill Embedding Probe

▸ Glove Fasttext Subword

▸ Assets

▸ Code

▸ Docs

MGloVe, FastText, and Subword Embeddings

▸ Outputs

MSkill Embeddings Picker

▸ Sentiment Analysis

▸ Assets

▸ Code

▸ Docs

MSentiment Analysis

▸ Outputs

MPrompt Sentiment Baseline

▸ Named Entity Recognition

▸ Assets

▸ Code

▸ Docs

MNamed Entity Recognition

▸ Outputs

MSkill Ner Picker

▸ Pos Tagging Parsing

▸ Assets

▸ Code

▸ Docs

MPOS Tagging and Syntactic Parsing

▸ Outputs

MSkill Grammar Pipeline

▸ Cnns Rnns For Text

▸ Assets

▸ Code

▸ Docs

MCNNs and RNNs for Text

▸ Outputs

MPrompt Text Encoder Picker

▸ Sequence To Sequence

▸ Assets

▸ Code

▸ Docs

MSequence-to-Sequence Models

▸ Outputs

MPrompt Seq2seq Design

▸ Attention Mechanism

▸ Assets

▸ Code

▸ Docs

MAttention Mechanism — The Breakthrough

▸ Outputs

MPrompt Attention Shapes

▸ Machine Translation

▸ Assets

▸ Code

▸ Docs

MMachine Translation

▸ Outputs

MSkill Mt Evaluator

▸ Text Summarization

▸ Assets

▸ Code

▸ Docs

MText Summarization

▸ Outputs

MSkill Summary Picker

▸ Question Answering

▸ Assets

▸ Code

▸ Docs

MQuestion Answering Systems

▸ Outputs

MSkill Qa Architect

▸ Information Retrieval Search

▸ Assets

▸ Code

▸ Docs

MInformation Retrieval and Search

▸ Outputs

MSkill Retrieval Picker

▸ Topic Modeling

▸ Assets

▸ Code

▸ Docs

MTopic Modeling — LDA and BERTopic

▸ Outputs

MSkill Topic Picker

▸ Text Generation Pre Transformer

▸ Assets

▸ Code

▸ Docs

MText Generation Before Transformers — N-gram Language Models

▸ Outputs

MPrompt Lm Baseline

▸ Chatbots Rule To Neural

▸ Assets

▸ Code

▸ Docs

MChatbots — Rule-Based to Neural to LLM Agents

▸ Outputs

MSkill Chatbot Architect

▸ Multilingual Nlp

▸ Assets

▸ Code

▸ Docs

MMultilingual NLP

▸ Outputs

MSkill Multilingual Picker

▸ Subword Tokenization

▸ Assets

▸ Code

{ }Main { }Main

▸ Docs

MSubword Tokenization — BPE, WordPiece, Unigram, SentencePiece

▸ Outputs

MSkill Bpe Vs Wordpiece

▸ Structured Outputs Constrained Decoding

▸ Assets

▸ Code

▸ Docs

MStructured Outputs & Constrained Decoding

▸ Outputs

MSkill Structured Output Picker

▸ Nli Textual Entailment

▸ Assets

▸ Code

▸ Docs

MNatural Language Inference — Textual Entailment

▸ Outputs

MSkill Nli Picker

▸ Embedding Models Deep Dive

▸ Assets

▸ Code

▸ Docs

MEmbedding Models — The 2026 Deep Dive

▸ Outputs

MSkill Embedding Picker

▸ Chunking Strategies Rag

▸ Assets

▸ Code

{ }Main { }Main

▸ Docs

MChunking Strategies for RAG

▸ Outputs

▸ Coreference Resolution

▸ Assets

▸ Code

▸ Docs

MCoreference Resolution

▸ Outputs

MSkill Coref Picker

▸ Entity Linking

▸ Assets

▸ Code

▸ Docs

MEntity Linking & Disambiguation

▸ Outputs

MSkill Entity Linker

▸ Relation Extraction Kg

▸ Assets

▸ Code

▸ Docs

MRelation Extraction & Knowledge Graph Construction

▸ Outputs

MSkill Re Designer

▸ Llm Evaluation Frameworks

▸ Assets

▸ Code

▸ Docs

MLLM Evaluation — RAGAS, DeepEval, G-Eval

▸ Outputs

MSkill Eval Architect

▸ Long Context Evaluation

▸ Assets

▸ Code

▸ Docs

MLong-Context Evaluation — NIAH, RULER, LongBench, MRCR

▸ Outputs

MSkill Long Context Eval

▸ Dialogue State Tracking

▸ Assets

▸ Code

▸ Docs

MDialogue State Tracking

▸ Outputs

MSkill Dst Designer

▸ Speech And Audio

▸ Audio Fundamentals

▸ Assets

▸ Code

▸ Docs

MAudio Fundamentals — Waveforms, Sampling, Fourier Transform

▸ Outputs

MSkill Audio Loader

▸ Spectrograms Mel Features

▸ Assets

▸ Code

▸ Docs

MSpectrograms, Mel Scale & Audio Features

▸ Outputs

MSkill Feature Extractor

▸ Audio Classification

▸ Assets

▸ Code

▸ Docs

MAudio Classification — From k-NN on MFCCs to AST and BEATs

▸ Outputs

MSkill Classifier Designer

▸ Speech Recognition Asr

▸ Assets

▸ Code

▸ Docs

MSpeech Recognition (ASR) — CTC, RNN-T, Attention

▸ Outputs

MSkill Asr Picker

▸ Whisper Architecture Finetuning

▸ Assets

▸ Code

▸ Docs

MWhisper — Architecture & Fine-Tuning

▸ Outputs

MSkill Whisper Tuner

▸ Speaker Recognition Verification

▸ Assets

▸ Code

▸ Docs

MSpeaker Recognition & Verification

▸ Outputs

MSkill Speaker Verifier

▸ Text To Speech

▸ Assets

▸ Code

▸ Docs

MText-to-Speech (TTS) — From Tacotron to F5 and Kokoro

▸ Outputs

MSkill Tts Designer

▸ Voice Cloning Conversion

▸ Assets

▸ Code

▸ Docs

MVoice Cloning & Voice Conversion

▸ Outputs

MSkill Voice Cloner

▸ Music Generation

▸ Assets

▸ Code

▸ Docs

MMusic Generation — MusicGen, Stable Audio, Suno, and the Licensing Earthquake

▸ Outputs

MSkill Music Designer

▸ Audio Language Models

▸ Assets

▸ Code

▸ Docs

MAudio-Language Models — Qwen2.5-Omni, Audio Flamingo, GPT-4o Audio

▸ Outputs

MSkill Alm Picker

▸ Real Time Audio Processing

▸ Assets

▸ Code

{ }Main { }Main

▸ Docs

MReal-Time Audio Processing

▸ Outputs

MSkill Realtime Pipeline

▸ Voice Assistant Pipeline

▸ Assets

▸ Code

▸ Docs

MBuild a Voice Assistant Pipeline — The Phase 6 Capstone

▸ Outputs

MSkill Voice Assistant Architect

▸ Neural Audio Codecs

▸ Assets

▸ Code

▸ Docs

MNeural Audio Codecs — EnCodec, SNAC, Mimi, DAC and the Semantic-Acoustic Split

▸ Outputs

MSkill Codec Picker

▸ Voice Activity Detection Turn Taking

▸ Assets

▸ Code

▸ Docs

MVoice Activity Detection & Turn-Taking — Silero, Cobra, and the Flush Trick

▸ Outputs

MSkill Vad Tuner

▸ Streaming Speech To Speech Moshi Hibiki

▸ Assets

▸ Code

▸ Docs

MStreaming Speech-to-Speech — Moshi, Hibiki, and Full-Duplex Dialogue

▸ Outputs

MSkill Duplex Pipeline

▸ Anti Spoofing Audio Watermarking

▸ Assets

▸ Code

▸ Docs

MVoice Anti-Spoofing & Audio Watermarking — ASVspoof 5, AudioSeal, WaveVerify

▸ Outputs

MSkill Spoof Defender

▸ Audio Evaluation Metrics

▸ Assets

▸ Code

▸ Docs

MAudio Evaluation — WER, MOS, UTMOS, MMAU, FAD, and the Open Leaderboards

▸ Outputs

MSkill Audio Evaluator

▸ Transformers Deep Dive

▸ Why Transformers

▸ Assets

▸ Code

▸ Docs

MWhy Transformers — The Problems with RNNs

▸ Outputs

MSkill Architecture Picker

▸ Self Attention From Scratch

▸ Code

{ }Main { }Self Attention

▸ Docs

MSelf-Attention from Scratch

▸ Outputs

MPrompt Attention Explainer

▸ Multi Head Attention

▸ Assets

▸ Code

{ }Main { }Main

▸ Docs

MMulti-Head Attention

▸ Outputs

MSkill Mha Configurator

▸ Positional Encoding

▸ Assets

▸ Code

{ }Main { }Main

▸ Docs

MPositional Encoding — Sinusoidal, RoPE, ALiBi

▸ Outputs

MSkill Positional Encoding Picker

▸ Full Transformer

▸ Assets

▸ Code

▸ Docs

MThe Full Transformer — Encoder + Decoder

▸ Outputs

MSkill Transformer Block Reviewer

▸ Bert Masked Language Modeling

▸ Assets

▸ Code

▸ Docs

MBERT — Masked Language Modeling

▸ Outputs

MSkill Bert Finetuner

▸ Gpt Causal Language Modeling

▸ Assets

▸ Code

▸ Docs

MGPT — Causal Language Modeling

▸ Outputs

MSkill Sampling Tuner

▸ T5 Bart Encoder Decoder

▸ Assets

▸ Code

▸ Docs

MT5, BART — Encoder-Decoder Models

▸ Outputs

MSkill Seq2seq Picker

▸ Vision Transformers

▸ Assets

▸ Code

▸ Docs

MVision Transformers (ViT)

▸ Outputs

MSkill Vit Configurator

▸ Audio Transformers Whisper

▸ Assets

▸ Code

▸ Docs

MAudio Transformers — Whisper Architecture

▸ Outputs

MSkill Asr Configurator

▸ Mixture Of Experts

▸ Assets

▸ Code

▸ Docs

MMixture of Experts (MoE)

▸ Outputs

MSkill Moe Configurator

▸ Kv Cache Flash Attention

▸ Assets

▸ Code

▸ Docs

MKV Cache, Flash Attention & Inference Optimization

▸ Outputs

MSkill Inference Optimizer

▸ Scaling Laws

▸ Assets

▸ Code

▸ Docs

▸ Outputs

MSkill Training Budget Estimator

▸ Build A Transformer Capstone

▸ Assets

▸ Code

▸ Docs

MBuild a Transformer from Scratch — The Capstone

▸ Outputs

MSkill Transformer Review

▸ Attention Variants

▸ Code

▸ Docs

MAttention Variants — Sliding Window, Sparse, Differential

▸ Outputs

MAttention Variant Picker

▸ Speculative Decoding

▸ Code

▸ Docs

MSpeculative Decoding — Draft, Verify, Repeat

▸ Outputs

MSpeculative Decoding Picker

▸ Generative Ai

▸ Generative Models Taxonomy History

▸ Assets

▸ Code

▸ Docs

MGenerative Models — Taxonomy & History

▸ Outputs

MSkill Model Chooser

▸ Autoencoders Vae

▸ Assets

▸ Code

▸ Docs

MAutoencoders & Variational Autoencoders (VAE)

▸ Outputs

MSkill Vae Trainer

▸ Gans Generator Discriminator

▸ Assets

▸ Code

▸ Docs

MGANs — Generator vs Discriminator

▸ Outputs

MSkill Gan Debugger

▸ Conditional Gans Pix2pix

▸ Assets

▸ Code

▸ Docs

MConditional GANs & Pix2Pix

▸ Outputs

MSkill Img2img Chooser

▸ Stylegan

▸ Assets

▸ Code

▸ Docs

▸ Outputs

MSkill Stylegan Inversion

▸ Diffusion Ddpm From Scratch

▸ Assets

▸ Code

▸ Docs

MDiffusion Models — DDPM from Scratch

▸ Outputs

MSkill Diffusion Trainer

▸ Latent Diffusion Stable Diffusion

▸ Assets

▸ Code

▸ Docs

MLatent Diffusion & Stable Diffusion

▸ Outputs

MSkill Sd Prompter

▸ Controlnet Lora Conditioning

▸ Assets

▸ Code

▸ Docs

MControlNet, LoRA & Conditioning

▸ Outputs

MSkill Sd Toolkit Composer

▸ Inpainting Outpainting Editing

▸ Assets

▸ Code

▸ Docs

MInpainting, Outpainting & Image Editing

▸ Outputs

MSkill Editing Pipeline

▸ Video Generation

▸ Assets

▸ Code

▸ Docs

MVideo Generation

▸ Outputs

MSkill Video Brief

▸ Audio Generation

▸ Assets

▸ Code

▸ Docs

MAudio Generation

▸ Outputs

MSkill Audio Brief

▸ 3d Generation

▸ Assets

▸ Code

▸ Docs

▸ Outputs

MSkill 3d Pipeline

▸ Flow Matching Rectified Flows

▸ Assets

▸ Code

▸ Docs

MFlow Matching & Rectified Flows

▸ Outputs

MSkill Fm Tuner

▸ Evaluation Fid Clip Score

▸ Assets

▸ Code

▸ Docs

MEvaluation — FID, CLIP Score, Human Preference

▸ Outputs

MSkill Eval Report

▸ Visual Autoregressive Var

▸ Code

▸ Docs

MVisual Autoregressive Modeling (VAR): Next-Scale Prediction

▸ Outputs

MSkill Var Tokenizer Designer

▸ Reinforcement Learning

▸ Mdps States Actions Rewards

▸ Assets

▸ Code

▸ Docs

MMDPs, States, Actions & Rewards

▸ Outputs

MSkill Mdp Modeler

▸ Dynamic Programming

▸ Assets

▸ Code

▸ Docs

MDynamic Programming — Policy Iteration & Value Iteration

▸ Outputs

MSkill Dp Solver

▸ Monte Carlo Methods

▸ Assets

▸ Code

▸ Docs

MMonte Carlo Methods — Learning from Complete Episodes

▸ Outputs

MSkill Mc Evaluator

▸ Q Learning Sarsa

▸ Assets

▸ Code

▸ Docs

MTemporal Difference — Q-Learning & SARSA

▸ Outputs

MSkill Td Agent

▸ Dqn

▸ Assets

▸ Code

▸ Docs

MDeep Q-Networks (DQN)

▸ Outputs

MSkill Dqn Trainer

▸ Policy Gradients Reinforce

▸ Assets

▸ Code

▸ Docs

MPolicy Gradient — REINFORCE from Scratch

▸ Outputs

MSkill Policy Gradient Trainer

▸ Actor Critic A2c A3c

▸ Assets

▸ Code

▸ Docs

MActor-Critic — A2C and A3C

▸ Outputs

MSkill Actor Critic Trainer

▸ Ppo

▸ Assets

▸ Code

▸ Docs

MProximal Policy Optimization (PPO)

▸ Outputs

MSkill Ppo Trainer

▸ Reward Modeling Rlhf

▸ Assets

▸ Code

▸ Docs

MReward Modeling & RLHF

▸ Outputs

MSkill Rlhf Architect

▸ Multi Agent Rl

▸ Assets

▸ Code

▸ Docs

MMulti-Agent RL

▸ Outputs

MSkill Marl Architect

▸ Sim To Real Transfer

▸ Assets

▸ Code

▸ Docs

MSim-to-Real Transfer

▸ Outputs

MSkill Sim2real Planner

▸ Rl For Games

▸ Assets

▸ Code

▸ Docs

MRL for Games — AlphaZero, MuZero, and the LLM-Reasoning Era

▸ Outputs

MSkill Game Rl Designer

▸ Llms From Scratch

▸ Tokenizers

▸ Code

{ }Bpe { }Bpe { }Main

▸ Docs

MTokenizers: BPE, WordPiece, SentencePiece

▸ Outputs

MPrompt Tokenizer Analyzer MTokenizer Selection and Implementation

▸ Building A Tokenizer

▸ Code

▸ Docs

MBuilding a Tokenizer from Scratch

▸ Outputs

MProduction Tokenizer Builder

▸ Data Pipelines

▸ Code

▸ Docs

MData Pipelines for Pre-Training

▸ Outputs

MData Quality Checker for LLM Pre-Training

▸ Pre Training Mini Gpt

▸ Code

{ }Main { }Main

▸ Docs

MPre-Training a Mini GPT (124M Parameters)

▸ Outputs

MGPT Architecture Analyzer

▸ Scaling Distributed

▸ Code

▸ Docs

MScaling: Distributed Training, FSDP, DeepSpeed

▸ Outputs

MDistributed Training Planner

▸ Instruction Tuning Sft

▸ Code

▸ Docs

MInstruction Tuning (SFT)

▸ Outputs

MSFT Data Curator

▸ Rlhf

▸ Code

▸ Docs

MRLHF: Reward Model + PPO

▸ Outputs

MReward Model Designer

▸ Dpo

▸ Code

▸ Docs

MDPO: Direct Preference Optimization

▸ Outputs

MAlignment Method Selector

▸ Constitutional Ai Self Improvement

▸ Assets

▸ Code

▸ Docs

MConstitutional AI and Self-Improvement

▸ Outputs

MSkill Self Improvement Auditor

▸ Evaluation

▸ Code

▸ Docs

MEvaluation: Benchmarks, Evals, LM Harness

▸ Outputs

MPrompt Eval Designer MLLM Evaluation Strategy

▸ Quantization

▸ Code

{ }Main { }Main

▸ Docs

MQuantization: Making Models Fit

▸ Outputs

MQuantization Decision Framework

▸ Inference Optimization

▸ Code

{ }Main { }Main

▸ Docs

MInference Optimization

▸ Outputs

MLLM Inference Optimization Pattern

▸ Building Complete Llm Pipeline

▸ Assets

▸ Code

▸ Docs

MBuilding a Complete LLM Pipeline

▸ Outputs

MSkill Llm Pipeline Reviewer

▸ Open Models Architecture Walkthroughs

▸ Assets

▸ Code

▸ Docs

MOpen Models: Architecture Walkthroughs

▸ Outputs

MSkill Open Model Picker

▸ Speculative Decoding Eagle3

▸ Assets

▸ Code

▸ Docs

MSpeculative Decoding and EAGLE-3

▸ Outputs

MSkill Eagle3 Tuner

▸ Differential Attention V2

▸ Assets

▸ Code

▸ Docs

MDifferential Attention (V2)

▸ Outputs

MSkill Diff Attention Integrator

▸ Native Sparse Attention

▸ Assets

▸ Code

▸ Docs

MNative Sparse Attention (DeepSeek NSA)

▸ Outputs

MSkill Nsa Integrator

▸ Multi Token Prediction

▸ Assets

▸ Code

▸ Docs

MMulti-Token Prediction (MTP)

▸ Outputs

MSkill Mtp Planner

▸ Dualpipe Parallelism

▸ Assets

▸ Code

▸ Docs

MDualPipe Parallelism

▸ Outputs

MSkill Dualpipe Planner

▸ Deepseek V3 Walkthrough

▸ Assets

▸ Code

▸ Docs

MDeepSeek-V3 Architecture Walkthrough

▸ Outputs

MSkill Deepseek V3 Reader

▸ Jamba Hybrid Ssm Transformer

▸ Assets

▸ Code

▸ Docs

MJamba — Hybrid SSM-Transformer

▸ Outputs

MSkill Hybrid Picker

▸ Async Hogwild Inference

▸ Assets

▸ Code

▸ Docs

MAsync and Hogwild! Inference

▸ Outputs

MSkill Parallel Inference Router

▸ Speculative Decoding

▸ Code

▸ Docs

MSpeculative Decoding and EAGLE

▸ Outputs

MSkill Speculative Tuning

▸ Gradient Checkpointing

▸ Code

▸ Docs

MGradient Checkpointing and Activation Recomputation

▸ Outputs

MSkill Checkpointing Planner

▸ Llm Engineering

▸ Prompt Engineering

▸ Code

{ }Main { }Prompt Engineering

▸ Docs

MPrompt Engineering: Techniques & Patterns

▸ Outputs

MPrompt Prompt Optimizer MPrompt Pattern Selection Guide

▸ Few Shot Cot

▸ Code

{ }Advanced Prompting

▸ Docs

MFew-Shot, Chain-of-Thought, Tree-of-Thought

▸ Outputs

MPrompt Reasoning Chain MReasoning Technique Selection Guide

▸ Structured Outputs

▸ Code

{ }Main { }Main

▸ Docs

MStructured Outputs: JSON, Schema Validation, Constrained Decoding

▸ Outputs

MPrompt Structured Extractor MStructured Output Strategy

▸ Embeddings

▸ Code

{ }Embeddings { }Main

▸ Docs

MEmbeddings & Vector Representations

▸ Outputs

MPrompt Embedding Advisor MEmbedding Patterns

▸ Context Engineering

▸ Code

{ }Main { }Main

▸ Docs

MContext Engineering: Windows, Budgets, Memory, and Retrieval

▸ Outputs

MPrompt Context Optimizer MContext Engineering

▸ Rag

▸ Code

{ }Main { }Main

▸ Docs

MRAG (Retrieval-Augmented Generation)

▸ Outputs

MPrompt Rag Architect MRAG Pipeline Pattern

▸ Advanced Rag

▸ Code

▸ Docs

MAdvanced RAG (Chunking, Reranking, Hybrid Search)

▸ Outputs

MPrompt Advanced Rag Debugger MAdvanced RAG Pattern

▸ Fine Tuning Lora

▸ Code

▸ Docs

MFine-Tuning with LoRA & QLoRA

▸ Outputs

MPrompt Lora Advisor MFine-Tuning Decision Guide

▸ Function Calling

▸ Code

{ }Function Calling { }Main

▸ Docs

MFunction Calling & Tool Use

▸ Outputs

MPrompt Tool Designer MFunction Calling Patterns

▸ Evaluation

▸ Code

{ }Eval Framework

▸ Docs

MEvaluation & Testing LLM Applications

▸ Outputs

MPrompt Eval Designer MEval Patterns

▸ Caching Cost

▸ Code

{ }Caching Cost

▸ Docs

MCaching, Rate Limiting & Cost Optimization

▸ Outputs

MPrompt Cost Optimizer MLLM Cost Optimization Patterns

▸ Guardrails

▸ Code

{ }Guardrails { }Main

▸ Docs

MGuardrails, Safety & Content Filtering

▸ Outputs

MPrompt Safety Auditor MGuardrail Patterns

▸ Production App

▸ Code

{ }Production App

▸ Docs

MBuilding a Production LLM Application

▸ Outputs

MPrompt Architecture Reviewer MProduction LLM Checklist

▸ Model Context Protocol

▸ Assets

▸ Code

▸ Docs

MModel Context Protocol (MCP)

▸ Outputs

MSkill Mcp Server Designer

▸ Prompt Caching

▸ Assets

▸ Code

▸ Docs

MPrompt Caching and Context Caching

▸ Outputs

MSkill Prompt Caching Planner

▸ Langgraph State Machines

▸ Assets

▸ Code

▸ Docs

MLangGraph — State Machines for Agents

▸ Outputs

MSkill Stategraph Designer

▸ Agent Framework Tradeoffs

▸ Assets

▸ Code

▸ Docs

MAgent Framework Tradeoffs — LangGraph vs CrewAI vs AutoGen vs Agno

▸ Outputs

MSkill Framework Picker

▸ Multimodal Ai

▸ Vision Transformer Patch Tokens

▸ Assets

▸ Code

▸ Docs

MVision Transformers and the Patch-Token Primitive

▸ Outputs

MSkill Patch Geometry Reader

▸ Clip Contrastive Pretraining

▸ Assets

▸ Code

▸ Docs

MCLIP and Contrastive Vision-Language Pretraining

▸ Outputs

MSkill Clip Zero Shot

▸ Blip2 Qformer Bridge

▸ Assets

▸ Code

▸ Docs

MFrom CLIP to BLIP-2 — Q-Former as Modality Bridge

▸ Outputs

MSkill Modality Bridge Picker

▸ Flamingo Gated Cross Attention

▸ Assets

▸ Code

▸ Docs

MFlamingo and Gated Cross-Attention for Few-Shot VLMs

▸ Outputs

MSkill Gated Bridge Diagnostic

▸ Llava Visual Instruction Tuning

▸ Assets

▸ Code

▸ Docs

MLLaVA and Visual Instruction Tuning

▸ Outputs

MSkill Llava Vibes Eval

▸ Any Resolution Patch N Pack

▸ Assets

▸ Code

▸ Docs

MAny-Resolution Vision: Patch-n'-Pack and NaFlex

▸ Outputs

MSkill Resolution Budget Planner

▸ Open Weight Vlm Recipes

▸ Assets

▸ Code

▸ Docs

MOpen-Weight VLM Recipes: What Actually Matters

▸ Outputs

MSkill Vlm Recipe Picker

▸ Llava Onevision Single Multi Video

▸ Assets

▸ Code

▸ Docs

MLLaVA-OneVision: Single-Image, Multi-Image, Video in One Model

▸ Outputs

MSkill Onevision Budget Planner

▸ Qwen Vl Family Dynamic Fps

▸ Assets

▸ Code

▸ Docs

MQwen-VL Family and Dynamic-FPS Video

▸ Outputs

MSkill Qwen Vl Pipeline Designer

▸ Internvl3 Native Multimodal

▸ Assets

▸ Code

▸ Docs

MInternVL3: Native Multimodal Pretraining

▸ Outputs

MSkill Native Vs Posthoc Auditor

▸ Chameleon Early Fusion Tokens

▸ Assets

▸ Code

▸ Docs

MChameleon and Early-Fusion Token-Only Multimodal Models

▸ Outputs

MSkill Tokenizer Vs Adapter Picker

▸ Emu3 Next Token For Generation

▸ Assets

▸ Code

▸ Docs

MEmu3: Next-Token Prediction for Image and Video Generation

▸ Outputs

MSkill Token Gen Cost Analyzer

▸ Transfusion Autoregressive Diffusion

▸ Assets

▸ Code

▸ Docs

MTransfusion: Autoregressive Text + Diffusion Image in One Transformer

▸ Outputs

MSkill Two Loss Trainer Designer

▸ Show O Discrete Diffusion Unified

▸ Assets

▸ Code

▸ Docs

MShow-o and Discrete-Diffusion Unified Models

▸ Outputs

MSkill Unified Gen Model Picker

▸ Janus Pro Decoupled Encoders

▸ Assets

▸ Code

▸ Docs

MJanus-Pro: Decoupled Encoders for Unified Multimodal Models

▸ Outputs

MSkill Decoupled Encoder Picker

▸ Mio Any To Any Streaming

▸ Assets

▸ Code

▸ Docs

MMIO and Any-to-Any Streaming Multimodal Models

▸ Outputs

MSkill Any To Any Pipeline Auditor

▸ Video Language Temporal Grounding

▸ Assets

▸ Code

▸ Docs

MVideo-Language Models: Temporal Tokens and Grounding

▸ Outputs

MSkill Video Vlm Frame Planner

▸ Long Video Million Token

▸ Assets

▸ Code

▸ Docs

MLong-Video Understanding at Million-Token Context

▸ Outputs

MSkill Long Video Strategy Planner

▸ Audio Language Whisper To Af3

▸ Assets

▸ Code

▸ Docs

MAudio-Language Models: the Whisper to Audio Flamingo 3 Arc

▸ Outputs

MSkill Audio Llm Pipeline Picker

▸ Omni Models Thinker Talker

▸ Assets

▸ Code

▸ Docs

MOmni Models: Qwen2.5-Omni and the Thinker-Talker Split

▸ Outputs

MSkill Omni Streaming Budget

▸ Embodied Vlas Openvla Pi0 Groot

▸ Assets

▸ Code

▸ Docs

MEmbodied VLAs: RT-2, OpenVLA, π0, GR00T

▸ Outputs

MSkill Vla Action Format Picker

▸ Document Diagram Understanding

▸ Assets

▸ Code

▸ Docs

MDocument and Diagram Understanding

▸ Outputs

MSkill Document Ai Stack Picker

▸ Colpali Vision Native Rag

▸ Assets

▸ Code

▸ Docs

MColPali and Vision-Native Document RAG

▸ Outputs

MSkill Vision Rag Designer

▸ Multimodal Rag Cross Modal

▸ Assets

▸ Code

▸ Docs

MMultimodal RAG and Cross-Modal Retrieval

▸ Outputs

MSkill Multimodal Rag Designer

▸ Multimodal Agents Computer Use

▸ Assets

▸ Code

▸ Docs

MMultimodal Agents and Computer-Use (Capstone)

▸ Outputs

MSkill Multimodal Agent Designer

▸ Tools And Protocols

▸ The Tool Interface

▸ Assets

▸ Code

{ }Main { }Main

▸ Docs

MThe Tool Interface — Why Agents Need Structured I/O

▸ Outputs

MSkill Tool Interface Reviewer

▸ Function Calling Deep Dive

▸ Assets

▸ Code

▸ Docs

MFunction Calling Deep Dive — OpenAI, Anthropic, Gemini

▸ Outputs

MSkill Provider Portability Audit

▸ Parallel And Streaming Tool Calls

▸ Assets

▸ Code

▸ Docs

MParallel Tool Calls and Streaming with Tools

▸ Outputs

MSkill Parallel Call Safety Check

▸ Structured Output

▸ Assets

▸ Code

▸ Docs

MStructured Output — JSON Schema, Pydantic, Zod, Constrained Decoding

▸ Outputs

MSkill Structured Output Designer

▸ Tool Schema Design

▸ Assets

▸ Code

▸ Docs

MTool Schema Design — Naming, Descriptions, Parameter Constraints

▸ Outputs

MSkill Tool Schema Linter

▸ Mcp Fundamentals

▸ Assets

▸ Code

▸ Docs

MMCP Fundamentals — Primitives, Lifecycle, JSON-RPC Base

▸ Outputs

MSkill Mcp Handshake Tracer

▸ Building An Mcp Server

▸ Assets

▸ Code

{ }Main { }Main

▸ Docs

MBuilding an MCP Server — Python + TypeScript SDKs

▸ Outputs

MSkill Mcp Server Scaffolder

▸ Building An Mcp Client

▸ Assets

▸ Code

▸ Docs

MBuilding an MCP Client — Discovery, Invocation, Session Management

▸ Outputs

MSkill Mcp Client Harness

▸ Mcp Transports

▸ Assets

▸ Code

▸ Docs

MMCP Transports — stdio vs Streamable HTTP vs SSE Migration

▸ Outputs

MSkill Mcp Transport Migrator

▸ Mcp Resources And Prompts

▸ Assets

▸ Code

▸ Docs

MMCP Resources and Prompts — Context Exposure Beyond Tools

▸ Outputs

MSkill Primitive Splitter

▸ Mcp Sampling

▸ Assets

▸ Code

▸ Docs

MMCP Sampling — Server-Requested LLM Completions and Agent Loops

▸ Outputs

MSkill Sampling Loop Designer

▸ Mcp Roots And Elicitation

▸ Assets

▸ Code

▸ Docs

MRoots and Elicitation — Scoping and Mid-Flight User Input

▸ Outputs

MSkill Elicitation Form Designer

▸ Mcp Async Tasks

▸ Assets

▸ Code

▸ Docs

MAsync Tasks (SEP-1686) — Call-Now, Fetch-Later for Long-Running Work

▸ Outputs

MSkill Task Store Designer

▸ Mcp Apps

▸ Assets

▸ Code

▸ Docs

MMCP Apps — Interactive UI Resources via ui://

▸ Outputs

MSkill Mcp Apps Spec

▸ Mcp Security Tool Poisoning

▸ Assets

▸ Code

▸ Docs

MMCP Security I — Tool Poisoning, Rug Pulls, Cross-Server Shadowing

▸ Outputs

MSkill Mcp Threat Model

▸ Mcp Security Oauth 2 1

▸ Assets

▸ Code

▸ Docs

MMCP Security II — OAuth 2.1, Resource Indicators, Incremental Scopes

▸ Outputs

MSkill Oauth Scope Planner

▸ Mcp Gateways And Registries

▸ Assets

▸ Code

▸ Docs

MMCP Gateways and Registries — Enterprise Control Planes

▸ Outputs

MSkill Gateway Bootstrap

▸ Mcp Auth Production

▸ Assets

▸ Code

▸ Docs

MMCP Auth in Production — DCR, JWKS Rotation, Audience-Pinned Tokens on iii Primitives

▸ Outputs

MSkill Mcp Auth Iii

▸ A2a Protocol

▸ Assets

▸ Code

{ }Main { }Main

▸ Docs

MA2A — Agent-to-Agent Protocol

▸ Outputs

MSkill A2a Agent Spec

▸ Opentelemetry Genai

▸ Assets

▸ Code

▸ Docs

MOpenTelemetry GenAI — Tracing Tool Calls End-to-End

▸ Outputs

MSkill Otel Genai Instrumentation

▸ Llm Routing Layer

▸ Assets

▸ Code

▸ Docs

MLLM Routing Layer — LiteLLM, OpenRouter, Portkey

▸ Outputs

MSkill Routing Config Designer

▸ Skills And Agent Sdks

▸ Assets

▸ Code

▸ Docs

MSkills and Agent SDKs — Anthropic Skills, AGENTS.md, OpenAI Apps SDK

▸ Outputs

MSkill Agent Bundle

▸ Capstone Tool Ecosystem

▸ Assets

▸ Code

▸ Docs

MCapstone — Build a Complete Tool Ecosystem

▸ Outputs

MSkill Ecosystem Blueprint

▸ Agent Engineering

▸ The Agent Loop

▸ Assets

▸ Code

{ }Main { }Main

▸ Docs

MThe Agent Loop: Observe, Think, Act

▸ Outputs

MSkill Agent Loop

▸ Rewoo Plan And Execute

▸ Assets

▸ Code

▸ Docs

MReWOO and Plan-and-Execute: Decoupled Planning

▸ Outputs

MSkill Rewoo Planner

▸ Reflexion Verbal Rl

▸ Assets

▸ Code

▸ Docs

MReflexion: Verbal Reinforcement Learning

▸ Outputs

MSkill Reflexion Buffer

▸ Tree Of Thoughts Lats

▸ Assets

▸ Code

▸ Docs

MTree of Thoughts and LATS: Deliberate Search

▸ Outputs

MSkill Search Policy

▸ Self Refine And Critic

▸ Assets

▸ Code

▸ Docs

MSelf-Refine and CRITIC: Iterative Output Improvement

▸ Outputs

MSkill Refine Loop

▸ Tool Use And Function Calling

▸ Assets

▸ Code

{ }Main { }Main

▸ Docs

MTool Use and Function Calling

▸ Outputs

MSkill Tool Registry

▸ Memory Virtual Context Memgpt

▸ Assets

▸ Code

▸ Docs

MMemory: Virtual Context and MemGPT

▸ Outputs

MSkill Virtual Memory

▸ Memory Blocks Sleep Time Compute

▸ Assets

▸ Code

▸ Docs

MMemory Blocks and Sleep-Time Compute (Letta)

▸ Outputs

MSkill Memory Blocks

▸ Hybrid Memory Mem0

▸ Assets

▸ Code

▸ Docs

MHybrid Memory: Vector + Graph + KV (Mem0)

▸ Outputs

MSkill Hybrid Memory

▸ Skill Libraries Voyager

▸ Assets

▸ Code

▸ Docs

MSkill Libraries and Lifelong Learning (Voyager)

▸ Outputs

MSkill Skill Library

▸ Planning Htn And Evolutionary

▸ Assets

▸ Code

▸ Docs

MPlanning with HTN and Evolutionary Search

▸ Outputs

MSkill Hybrid Planner

▸ Anthropic Workflow Patterns

▸ Assets

▸ Code

▸ Docs

MAnthropic's Workflow Patterns: Simple Over Complex

▸ Outputs

MSkill Workflow Picker

▸ Langgraph Stateful Graphs

▸ Assets

▸ Code

{ }Main { }Main

▸ Docs

MLangGraph: Stateful Graphs and Durable Execution

▸ Outputs

MSkill State Graph

▸ Autogen Actor Model

▸ Assets

▸ Code

▸ Docs

MAutoGen v0.4: Actor Model and Agent Framework

▸ Outputs

MSkill Actor Runtime

▸ Crewai Role Based Crews

▸ Assets

▸ Code

▸ Docs

MCrewAI: Role-Based Crews and Flows

▸ Outputs

MSkill Crew Or Flow

▸ Openai Agents Sdk

▸ Assets

▸ Code

▸ Docs

MOpenAI Agents SDK: Handoffs, Guardrails, Tracing

▸ Outputs

MSkill Agents Sdk Scaffold

▸ Claude Agent Sdk

▸ Assets

▸ Code

▸ Docs

MClaude Agent SDK: Subagents and Session Store

▸ Outputs

MSkill Claude Agent Scaffold

▸ Agno And Mastra Runtimes

▸ Assets

▸ Code

{ }Main { }Main

▸ Docs

MAgno and Mastra: Production Runtimes

▸ Outputs

MSkill Runtime Picker

▸ Benchmarks Swebench Gaia

▸ Assets

▸ Code

▸ Docs

MBenchmarks: SWE-bench, GAIA, AgentBench

▸ Outputs

MSkill Benchmark Harness

▸ Benchmarks Webarena Osworld

▸ Assets

▸ Code

▸ Docs

MBenchmarks: WebArena and OSWorld

▸ Outputs

MSkill Web Desktop Harness

▸ Computer Use Agents

▸ Assets

▸ Code

▸ Docs

MComputer Use: Claude, OpenAI CUA, Gemini

▸ Outputs

MSkill Computer Use Safety

▸ Voice Agents Pipecat Livekit

▸ Assets

▸ Code

▸ Docs

MVoice Agents: Pipecat and LiveKit

▸ Outputs

MSkill Voice Pipeline

▸ Otel Genai Conventions

▸ Assets

▸ Code

▸ Docs

MOpenTelemetry GenAI Semantic Conventions

▸ Outputs

MSkill Otel Genai

▸ Agent Observability Platforms

▸ Assets

▸ Code

▸ Docs

MAgent Observability: Langfuse, Phoenix, Opik

▸ Outputs

MSkill Obs Platform Wiring

▸ Multi Agent Debate

▸ Assets

▸ Code

▸ Docs

MMulti-Agent Debate and Collaboration

▸ Outputs

▸ Failure Modes Agentic

▸ Assets

▸ Code

▸ Docs

MFailure Modes: Why Agents Break

▸ Outputs

MSkill Failure Detector

▸ Prompt Injection Defense

▸ Assets

▸ Code

▸ Docs

MPrompt Injection and the PVE Defense

▸ Outputs

MSkill Injection Defense

▸ Orchestration Patterns

▸ Assets

▸ Code

▸ Docs

MOrchestration Patterns: Supervisor, Swarm, Hierarchical

▸ Outputs

MSkill Orchestration Picker

▸ Production Runtimes

▸ Assets

▸ Code

▸ Docs

MProduction Runtimes: Queue, Event, Cron

▸ Outputs

MSkill Runtime Shape

▸ Eval Driven Agent Development

▸ Assets

▸ Code

▸ Docs

MEval-Driven Agent Development

▸ Outputs

MSkill Eval Suite

▸ Agent Workbench Why Models Fail

▸ Code

▸ Docs

MAgent Workbench Engineering: Why Capable Models Still Fail

MMission - Agent Workbench: Why Capable Models Still Fail

▸ Outputs

MSkill Workbench Audit

▸ Minimal Agent Workbench

▸ Code

▸ Docs

MThe Minimal Agent Workbench

MMission - The Minimal Agent Workbench

▸ Outputs

MSkill Minimal Workbench

▸ Instructions As Executable Constraints

▸ Code

MAgent Rules { }Main

▸ Docs

MAgent Instructions as Executable Constraints

MMission - Agent Instructions as Executable Constraints

▸ Outputs

MSkill Rule Set Builder

▸ Repo Memory And State

▸ Code

▸ Docs

MRepo Memory and Durable State

MMission - Repo Memory and Durable State

▸ Outputs

MSkill State Schema

▸ Initialization Scripts

▸ Code

▸ Docs

MInitialization Scripts for Agents

MMission - Initialization Scripts for Agents

▸ Outputs

MSkill Init Script

▸ Scope Contracts

▸ Code

▸ Docs

MScope Contracts and Task Boundaries

MMission - Scope Contracts and Task Boundaries

▸ Outputs

MSkill Scope Contract

▸ Runtime Feedback Loops

▸ Code

▸ Docs

MRuntime Feedback Loops

MMission - Runtime Feedback Loops

▸ Outputs

MSkill Feedback Runner

▸ Verification Gates

▸ Code

▸ Docs

MVerification Gates

MMission - Verification Gates

▸ Outputs

MSkill Verification Gate

▸ Reviewer Agent

▸ Code

▸ Docs

MReviewer Agent: Separate Builder from Marker

MMission - Reviewer Agent: Separate Builder from Marker

▸ Outputs

MSkill Reviewer Agent

▸ Multi Session Handoff

▸ Code

▸ Docs

MMulti-Session Handoff

MMission - Multi-Session Handoff

▸ Outputs

MSkill Handoff Generator

▸ Workbench For Real Repos

▸ Code

▸ Docs

MThe Workbench on a Real Repo

MMission - The Workbench on a Real Repo

▸ Outputs

MSkill Workbench Benchmark

▸ Agent Workbench Capstone

▸ Code

▸ Docs

MCapstone: Ship a Reusable Agent Workbench Pack

MMission - Capstone: Ship a Reusable Agent Workbench Pack

▸ Outputs

▸ Agent Workbench Pack

▸ Bin

▸ Docs

MAgent Rules MHandoff Protocol MReliability Policy MReviewer Rubric

▸ Schemas

{ }Agent State.schema { }Scope Contract.schema { }Task Board.schema

▸ Scripts

{ }Generate Handoff { }Init Agent { }Run With Feedback { }Verify Agent

MSkill Workbench Pack

▸ Autonomous Systems

▸ Long Horizon Agents

▸ Assets

▸ Code

▸ Docs

MThe Shift from Chatbots to Long-Horizon Agents

▸ Outputs

MSkill Horizon Reality Check

▸ Star Family Reasoning

▸ Assets

▸ Code

▸ Docs

MSTaR, V-STaR, Quiet-STaR — Self-Taught Reasoning

▸ Outputs

MSkill Star Loop Reviewer

▸ Alphaevolve Evolutionary Coding

▸ Assets

▸ Code

▸ Docs

MAlphaEvolve — Evolutionary Coding Agents

▸ Outputs

MSkill Evaluator Rigor Audit

▸ Darwin Godel Machine

▸ Assets

▸ Code

▸ Docs

MDarwin Godel Machine — Open-Ended Self-Modifying Agents

▸ Outputs

MSkill Dgm Evaluator Firewall

▸ Ai Scientist V2

▸ Assets

▸ Code

▸ Docs

MAI Scientist v2 — Workshop-Level Autonomous Research

▸ Outputs

MSkill Ai Scientist Sandbox Review

▸ Automated Alignment Research

▸ Assets

▸ Code

▸ Docs

MAutomated Alignment Research (Anthropic AAR)

▸ Outputs

MSkill Aar Deployment Review

▸ Recursive Self Improvement

▸ Assets

▸ Code

▸ Docs

MRecursive Self-Improvement — Capability vs Alignment

▸ Outputs

MSkill Rsi Cycle Pause Spec

▸ Bounded Self Improvement

▸ Assets

▸ Code

▸ Docs

MBounded Self-Improvement Designs

▸ Outputs

MSkill Bounded Loop Review

▸ Coding Agent Landscape

▸ Assets

▸ Code

▸ Docs

MThe Autonomous Coding Agent Landscape (2026)

▸ Outputs

MSkill Scaffold Audit

▸ Claude Code Permission Modes

▸ Assets

▸ Code

▸ Docs

MClaude Code as an Autonomous Agent: Permission Modes and Auto Mode

▸ Outputs

MSkill Permission Mode Picker

▸ Browser Agents

▸ Assets

▸ Code

▸ Docs

MBrowser Agents and Long-Horizon Web Tasks

▸ Outputs

MSkill Browser Agent Trust Boundary

▸ Durable Execution

▸ Assets

▸ Code

▸ Docs

MLong-Running Background Agents: Durable Execution

▸ Outputs

MSkill Durable Execution Review

▸ Cost Governors

▸ Assets

▸ Code

▸ Docs

MAction Budgets, Iteration Caps, and Cost Governors

▸ Outputs

MSkill Agent Budget Audit

▸ Kill Switches Canaries

▸ Assets

▸ Code

▸ Docs

MKill Switches, Circuit Breakers, and Canary Tokens

▸ Outputs

MSkill Tripwire Design

▸ Propose Then Commit

▸ Assets

▸ Code

▸ Docs

MHuman-in-the-Loop: Propose-Then-Commit

▸ Outputs

MSkill Hitl Design

▸ Checkpoints Rollback

▸ Assets

▸ Code

▸ Docs

MCheckpoints and Rollback

▸ Outputs

MSkill Rollback Rehearsal

▸ Constitutional Ai

▸ Assets

▸ Code

▸ Docs

MConstitutional AI and Rule Overrides

▸ Outputs

MSkill Constitution Review

▸ Llama Guard

▸ Assets

▸ Code

▸ Docs

MLlama Guard and Input/Output Classification

▸ Outputs

MSkill Classifier Stack Audit

▸ Anthropic Rsp

▸ Assets

▸ Code

▸ Docs

MAnthropic Responsible Scaling Policy v3.0

▸ Outputs

MSkill Scaling Policy Review

▸ Openai Preparedness Deepmind Fsf

▸ Assets

▸ Code

▸ Docs

MOpenAI Preparedness Framework and DeepMind Frontier Safety Framework

▸ Outputs

MSkill Cross Policy Diff

▸ Metr External Evaluation

▸ Assets

▸ Code

▸ Docs

MMETR Time Horizons and External Capability Evaluation

▸ Outputs

MSkill Horizon Interpretation

▸ Cais Caisi Societal Risk

▸ Assets

▸ Code

▸ Docs

MCAIS, CAISI, and Societal-Scale Risk

▸ Outputs

MSkill Societal Risk Review

▸ Multi Agent And Swarms

▸ Why Multi Agent

▸ Code

{ }Single Vs Multi

▸ Docs

MWhy Multi-Agent?

▸ Outputs

MPrompt Multi Agent Decision

▸ Fipa Acl Heritage

▸ Assets

▸ Code

▸ Docs

MHeritage of FIPA-ACL and Speech Acts

▸ Outputs

MSkill Fipa Mapper

▸ Communication Protocols

▸ Code

▸ Docs

MCommunication Protocols

▸ Outputs

MPrompt Protocol Selector

▸ Primitive Model

▸ Assets

▸ Code

▸ Docs

MThe Multi-Agent Primitive Model

▸ Outputs

MSkill Primitive Mapper

▸ Supervisor Orchestrator Pattern

▸ Assets

▸ Code

▸ Docs

MSupervisor / Orchestrator-Worker Pattern

▸ Outputs

MSkill Supervisor Designer

▸ Hierarchical Architecture

▸ Assets

▸ Code

▸ Docs

MHierarchical Architecture and Its Failure Mode

▸ Outputs

MSkill Hierarchy Fitness

▸ Society Of Mind Debate

▸ Assets

▸ Code

▸ Docs

MSociety of Mind and Multi-Agent Debate

▸ Outputs

MSkill Debate Configurator

▸ Role Specialization

▸ Assets

▸ Code

▸ Docs

MRole Specialization — Planner, Critic, Executor, Verifier

▸ Outputs

MSkill Role Designer

▸ Parallel Swarm Networks

▸ Assets

▸ Code

▸ Docs

MParallel / Swarm / Networked Architectures

▸ Outputs

MSkill Swarm Fit

▸ Group Chat Speaker Selection

▸ Assets

▸ Code

▸ Docs

MGroup Chat and Speaker Selection

▸ Outputs

MSkill Groupchat Selector

▸ Handoffs And Routines

▸ Assets

▸ Code

▸ Docs

MHandoffs and Routines — Stateless Orchestration

▸ Outputs

MSkill Handoff Designer

▸ A2a Protocol

▸ Assets

▸ Code

▸ Docs

MA2A — The Agent-to-Agent Protocol

▸ Outputs

MSkill A2a Integrator

▸ Shared Memory Blackboard

▸ Assets

▸ Code

▸ Docs

MShared Memory and Blackboard Patterns

▸ Outputs

MSkill Memory Auditor

▸ Consensus And Bft

▸ Assets

▸ Code

▸ Docs

MConsensus and Byzantine Fault Tolerance for Agents

▸ Outputs

MSkill Consensus Designer

▸ Voting Debate Topology

▸ Assets

▸ Code

▸ Docs

MVoting, Self-Consistency, and Debate Topology

▸ Outputs

MSkill Topology Picker

▸ Negotiation Bargaining

▸ Assets

▸ Code

▸ Docs

MNegotiation and Bargaining

▸ Outputs

MSkill Bargainer Designer

▸ Generative Agents Simulation

▸ Assets

▸ Code

▸ Docs

MGenerative Agents and Emergent Simulation

▸ Outputs

MSkill Simulation Designer

▸ Theory Of Mind Coordination

▸ Assets

▸ Code

▸ Docs

MTheory of Mind and Emergent Coordination

▸ Outputs

MSkill Tom Auditor

▸ Swarm Optimization Pso Aco

▸ Assets

▸ Code

▸ Docs

MSwarm Optimization for LLMs (PSO, ACO)

▸ Outputs

MSkill Swarm Optimizer

▸ Marl Maddpg Qmix Mappo

▸ Assets

▸ Code

▸ Docs

MMARL — MADDPG, QMIX, MAPPO

▸ Outputs

MSkill Marl Picker

▸ Agent Economies

▸ Assets

▸ Code

▸ Docs

MAgent Economies, Token Incentives, Reputation

▸ Outputs

MSkill Economy Designer

▸ Production Scaling Queues Checkpoints

▸ Assets

▸ Code

▸ Docs

MProduction Scaling — Queues, Checkpoints, Durability

▸ Outputs

MSkill Scaling Advisor

▸ Failure Modes Mast Groupthink

▸ Assets

▸ Code

▸ Docs

MFailure Modes — MAST, Groupthink, Monoculture, Cascading Errors

▸ Outputs

MSkill Mast Auditor

▸ Evaluation Coordination Benchmarks

▸ Assets

▸ Code

▸ Docs

MEvaluation and Coordination Benchmarks

▸ Outputs

MSkill Benchmark Reader

▸ Case Studies 2026 Sota

▸ Assets

▸ Code

▸ Docs

MCase Studies and the 2026 State of the Art

▸ Outputs

MSkill Case Study Mapper

▸ Infrastructure And Production

▸ Managed Llm Platforms

▸ Assets

▸ Code

▸ Docs

MManaged LLM Platforms — Bedrock, Vertex AI, Azure OpenAI

▸ Outputs

MSkill Managed Platform Picker

▸ Inference Platform Economics

▸ Assets

▸ Code

▸ Docs

MInference Platform Economics — Fireworks, Together, Baseten, Modal, Replicate, Anyscale

▸ Outputs

MSkill Inference Platform Picker

▸ Gpu Autoscaling Kubernetes

▸ Assets

▸ Code

▸ Docs

MGPU Autoscaling on Kubernetes — Karpenter, KAI Scheduler, Gang Scheduling

▸ Outputs

MSkill Gpu Autoscaler Plan

▸ Vllm Serving Internals

▸ Assets

▸ Code

▸ Docs

MvLLM Serving Internals: PagedAttention, Continuous Batching, Chunked Prefill

▸ Outputs

MSkill Vllm Scheduler Reader

▸ Eagle3 Speculative Decoding

▸ Assets

▸ Code

▸ Docs

MEAGLE-3 Speculative Decoding in Production

▸ Outputs

MSkill Eagle3 Rollout

▸ Sglang Radixattention

▸ Assets

▸ Code

▸ Docs

MSGLang and RadixAttention for Prefix-Heavy Workloads

▸ Outputs

MSkill Radix Scheduler Advisor

▸ Tensorrt Llm Blackwell

▸ Assets

▸ Code

▸ Docs

MTensorRT-LLM on Blackwell with FP8 and NVFP4

▸ Outputs

MSkill Trtllm Blackwell Advisor

▸ Inference Metrics Goodput

▸ Assets

▸ Code

▸ Docs

MInference Metrics — TTFT, TPOT, ITL, Goodput, P99

▸ Outputs

MSkill Slo Goodput Gate

▸ Production Quantization

▸ Assets

▸ Code

▸ Docs

MProduction Quantization — AWQ, GPTQ, GGUF K-quants, FP8, MXFP4/NVFP4

▸ Outputs

MSkill Quantization Picker

▸ Cold Start Mitigation

▸ Assets

▸ Code

▸ Docs

MCold Start Mitigation for Serverless LLMs

▸ Outputs

MSkill Cold Start Planner

▸ Multi Region Kv Locality

▸ Assets

▸ Code

▸ Docs

MMulti-Region LLM Serving and KV Cache Locality

▸ Outputs

MSkill Multi Region Router

▸ Edge Inference

▸ Assets

▸ Code

▸ Docs

MEdge Inference — Apple Neural Engine, Qualcomm Hexagon, WebGPU/WebLLM, Jetson

▸ Outputs

MSkill Edge Target Picker

▸ Llm Observability

▸ Assets

▸ Code

{ }Main { }Main

▸ Docs

MLLM Observability Stack Selection

▸ Outputs

MSkill Observability Stack

▸ Prompt Semantic Caching

▸ Assets

▸ Code

{ }Main { }Main

▸ Docs

MPrompt Caching and Semantic Caching Economics

▸ Outputs

MSkill Cache Auditor

▸ Batch Apis

▸ Assets

▸ Code

{ }Main { }Main

▸ Docs

MBatch APIs — the 50% Discount as Industry Standard

▸ Outputs

MSkill Batch Triager

▸ Model Routing

▸ Assets

▸ Code

{ }Main { }Main

▸ Docs

MModel Routing as a Cost-Reduction Primitive

▸ Outputs

MSkill Router Plan

▸ Disaggregated Prefill Decode

▸ Assets

▸ Code

▸ Docs

MDisaggregated Prefill/Decode — NVIDIA Dynamo and llm-d

▸ Outputs

MSkill Disaggregation Decider

▸ Vllm Production Stack Lmcache

▸ Assets

▸ Code

▸ Docs

MvLLM Production Stack with LMCache KV Offloading

▸ Outputs

MSkill Vllm Stack Decider

▸ Ai Gateways

▸ Assets

▸ Code

{ }Main { }Main

▸ Docs

MAI Gateways — LiteLLM, Portkey, Kong AI Gateway, Bifrost

▸ Outputs

MSkill Gateway Picker

▸ Shadow Canary Progressive

▸ Assets

▸ Code

{ }Main { }Main

▸ Docs

MShadow Traffic, Canary Rollout, and Progressive Deployment for LLMs

▸ Outputs

MSkill Rollout Runbook

▸ Ab Testing Llm Features

▸ Assets

▸ Code

▸ Docs

MA/B Testing LLM Features — GrowthBook, Statsig, and the Vibes Problem

▸ Outputs

▸ Load Testing Llm Apis

▸ Assets

▸ Code

▸ Docs

MLoad Testing LLM APIs — Why k6 and Locust Lie

▸ Outputs

MSkill Load Test Plan

▸ Sre For Ai

▸ Assets

▸ Code

▸ Docs

MSRE for AI — Multi-Agent Incident Response, Runbooks, Predictive Detection

▸ Outputs

MSkill Ai Sre Plan

▸ Chaos Engineering Llm

▸ Assets

▸ Code

▸ Docs

MChaos Engineering for LLM Production

▸ Outputs

MSkill Chaos Plan

▸ Security Secrets Audit

▸ Assets

▸ Code

▸ Docs

MSecurity — Secrets, API Key Rotation, Audit Logs, Guardrails

▸ Outputs

MSkill Llm Security Plan

▸ Compliance Frameworks

▸ Assets

▸ Code

▸ Docs

MCompliance — SOC 2, HIPAA, GDPR, PCI-DSS, EU AI Act, ISO 42001

▸ Outputs

MSkill Compliance Matrix

▸ Finops Llms

▸ Assets

▸ Code

▸ Docs

MFinOps for LLMs — Unit Economics and Multi-Tenant Attribution

▸ Outputs

MSkill Finops Plan

▸ Self Hosted Serving Selection

▸ Assets

▸ Code

▸ Docs

MSelf-Hosted Serving Selection — llama.cpp, Ollama, TGI, vLLM, SGLang

▸ Outputs

MSkill Engine Picker

▸ Ethics Safety Alignment

▸ Instruction Following Alignment Signal

▸ Assets

▸ Code

▸ Docs

MInstruction-Following as Alignment Signal

▸ Outputs

MSkill Instructgpt Explainer

▸ Reward Hacking Goodhart

▸ Assets

▸ Code

▸ Docs

MReward Hacking and Goodhart's Law

▸ Outputs

MSkill Reward Hack Auditor

▸ Direct Preference Optimization Family

▸ Assets

▸ Code

▸ Docs

MThe Direct Preference Optimization Family

▸ Outputs

MSkill Preference Loss Selector

▸ Sycophancy Rlhf Amplification

▸ Assets

▸ Code

▸ Docs

MSycophancy as RLHF Amplification

▸ Outputs

MSkill Sycophancy Probe

▸ Constitutional Ai Rlaif

▸ Assets

▸ Code

▸ Docs

MConstitutional AI and RLAIF

▸ Outputs

MSkill Constitution Writer

▸ Mesa Optimization Deceptive Alignment

▸ Assets

▸ Code

▸ Docs

MMesa-Optimization and Deceptive Alignment

▸ Outputs

MSkill Mesa Diagnostic

▸ Sleeper Agents Persistent Deception

▸ Assets

▸ Code

▸ Docs

MSleeper Agents — Persistent Deception

▸ Outputs

MSkill Sleeper Audit

▸ In Context Scheming Frontier Models

▸ Assets

▸ Code

▸ Docs

MIn-Context Scheming in Frontier Models

▸ Outputs

MSkill Scheming Triage

▸ Alignment Faking

▸ Assets

▸ Code

▸ Docs

MAlignment Faking

▸ Outputs

MSkill Compliance Gap

▸ Ai Control Subversion

▸ Assets

▸ Code

▸ Docs

MAI Control — Safety Despite Subversion

▸ Outputs

MSkill Control Protocol Audit

▸ Scalable Oversight Weak To Strong

▸ Assets

▸ Code

▸ Docs

MScalable Oversight and Weak-to-Strong Generalization

▸ Outputs

MSkill W2sg Pgr

▸ Red Teaming Pair Automated Attacks

▸ Assets

▸ Code

▸ Docs

MRed-Teaming: PAIR and Automated Attacks

▸ Outputs

MSkill Attack Audit

▸ Many Shot Jailbreaking

▸ Assets

▸ Code

▸ Docs

MMany-Shot Jailbreaking

▸ Outputs

MSkill Msj Audit

▸ Ascii Art Visual Jailbreaks

▸ Assets

▸ Code

▸ Docs

MASCII Art and Visual Jailbreaks

▸ Outputs

MSkill Encoding Audit

▸ Indirect Prompt Injection

▸ Assets

▸ Code

▸ Docs

MIndirect Prompt Injection — Production Attack Surface

▸ Outputs

MSkill Ipi Audit

▸ Red Team Tooling Garak Llamaguard Pyrit

▸ Assets

▸ Code

▸ Docs

MRed-Team Tooling — Garak, Llama Guard, PyRIT

▸ Outputs

MSkill Red Team Stack

▸ Wmdp Dual Use Evaluation

▸ Assets

▸ Code

▸ Docs

MWMDP and Dual-Use Capability Evaluation

▸ Outputs

MSkill Wmdp Eval

▸ Frontier Safety Frameworks Rsp Pf Fsf

▸ Assets

▸ Code

▸ Docs

MFrontier Safety Frameworks — RSP, PF, FSF

▸ Outputs

MSkill Framework Diff

▸ Model Welfare Research

▸ Assets

▸ Code

▸ Docs

MAnthropic's Model Welfare Program

▸ Outputs

MSkill Welfare Assessment

▸ Bias Representational Harm

▸ Assets

▸ Code

▸ Docs

MBias and Representational Harm in LLMs

▸ Outputs

MSkill Bias Eval

▸ Fairness Criteria Group Individual Counterfactual

▸ Assets

▸ Code

▸ Docs

MFairness Criteria — Group, Individual, Counterfactual

▸ Outputs

MSkill Fairness Criterion

▸ Differential Privacy For Llms

▸ Assets

▸ Code

▸ Docs

MDifferential Privacy for LLMs

▸ Outputs

MSkill Dp Audit

▸ Watermarking Synthid Stable Signature C2pa

▸ Assets

▸ Code

▸ Docs

MWatermarking — SynthID, Stable Signature, C2PA

▸ Outputs

MSkill Provenance Audit

▸ Regulatory Frameworks Eu Us Uk Korea

▸ Assets

▸ Code

▸ Docs

MRegulatory Frameworks — EU, US, UK, Korea

▸ Outputs

MSkill Regulatory Map

▸ Echoleak Cves For Ai

▸ Assets

▸ Code

▸ Docs

MEchoLeak and the Emergence of CVEs for AI

▸ Outputs

MSkill Cve Review

▸ Model System Dataset Cards

▸ Assets

▸ Code

▸ Docs

MModel, System, and Dataset Cards

▸ Outputs

MSkill Card Audit

▸ Data Provenance Training Governance

▸ Assets

▸ Code

▸ Docs

MData Provenance and Training-Data Governance

▸ Outputs

MSkill Provenance Check

▸ Alignment Research Ecosystem

▸ Assets

▸ Code

▸ Docs

MAlignment Research Ecosystem — MATS, Redwood, Apollo, METR

▸ Outputs

MSkill Ecosystem Map

▸ Moderation Systems Openai Perspective Llamaguard

▸ Assets

▸ Code

▸ Docs

MModeration Systems — OpenAI, Perspective, Llama Guard

▸ Outputs

MSkill Moderation Stack

▸ Dual Use Risk Cyber Bio Chem Nuclear

▸ Assets

▸ Code

▸ Docs

MDual-Use Risk — Cyber, Bio, Chem, Nuclear Uplift

▸ Outputs

MSkill Dual Use Triage

▸ Capstone Projects

▸ Terminal Native Coding Agent

▸ Assets

▸ Code

▸ Ts

▸ Src

{ }Eval { }Harness { }Hooks { }Index { }Model { }Plan { }Repl { }Tools { }Types

▸ Tests

{ }Harness.test { }Tools.test

▸ Docs

MCapstone 01 — Terminal-Native Coding Agent

▸ Outputs

MSkill Terminal Coding Agent

▸ Rag Over Codebase

▸ Assets

▸ Code

▸ Ts

▸ Src

{ }Corpus { }Index Store { }Index { }Retrieval { }Server { }Types

▸ Tests

{ }Index Store.test { }Retrieval.test { }Server.test

▸ Docs

MCapstone 02 — RAG over Codebase (Cross-Repo Semantic Search)

▸ Outputs

MSkill Codebase Rag

▸ Realtime Voice Assistant

▸ Assets

▸ Code

▸ Ts

▸ Src

{ }Index { }Orchestrator { }Protocol { }Server { }Types { }Vad

▸ Tests

{ }Orchestrator.test { }Protocol.test { }Vad.test

▸ Docs

MCapstone 03 — Real-Time Voice Assistant (ASR to LLM to TTS)

▸ Outputs

MSkill Voice Agent

▸ Multimodal Document Qa

▸ Assets

▸ Code

▸ Ts

▸ Src

{ }Fixtures { }Index { }Render { }Server { }Types

▸ Tests

{ }Fixtures.test { }Render.test { }Server.test

▸ Docs

MCapstone 04 — Multimodal Document QA (Vision-First PDF, Tables, Charts)

▸ Outputs

▸ Autonomous Research Agent

▸ Assets

▸ Code

▸ Docs

MCapstone 05 — Autonomous Research Agent (AI-Scientist Class)

▸ Outputs

MSkill Ai Scientist

▸ Devops Troubleshooting Agent

▸ Assets

▸ Code

▸ Ts

▸ Src

{ }Agent { }Blocks { }Index { }Server { }Slack Verify { }Types

▸ Tests

{ }Agent.test { }Server.test { }Slack Verify.test

▸ Docs

MCapstone 06 — DevOps Troubleshooting Agent for Kubernetes

▸ Outputs

MSkill Devops Agent

▸ End To End Fine Tuning Pipeline

▸ Assets

▸ Code

▸ Docs

MCapstone 07 — End-to-End Fine-Tuning Pipeline (Data to SFT to DPO to Serve)

▸ Outputs

MSkill Finetuning Pipeline

▸ Production Rag Chatbot

▸ Assets

▸ Code

▸ Ts

▸ Src

{ }Index { }Server { }Session { }Stream { }Types

▸ Tests

{ }Server.test { }Session.test { }Stream.test

▸ Docs

MCapstone 08 — Production RAG Chatbot for a Regulated Vertical

▸ Outputs

MSkill Production Rag

▸ Code Migration Agent

▸ Assets

▸ Code

▸ Ts

▸ Src

{ }Cost { }Index { }Migrations { }Server { }Types

▸ Tests

{ }Cost.test { }Migrations.test

▸ Docs

MCapstone 09 — Code Migration Agent (Repo-Level Language / Runtime Upgrade)

▸ Outputs

MSkill Migration Agent

▸ Multi Agent Software Team

▸ Assets

▸ Code

▸ Ts

▸ Src

{ }Agent { }Coordinator { }Index { }Runtime { }Types { }Workspace

▸ Tests

{ }Coordinator.test { }Runtime.test

▸ Docs

MCapstone 10 — Multi-Agent Software Engineering Team

▸ Outputs

MSkill Multi Agent Team

▸ Llm Observability Dashboard

▸ Assets

▸ Code

▸ Ts

▸ Src

{ }Index { }Pricing { }Rollup { }Server { }Spans { }Types

▸ Tests

{ }Rollup.test { }Spans.test

▸ Docs

MCapstone 11 — LLM Observability & Eval Dashboard

▸ Outputs

MSkill Llm Observability

▸ Video Understanding Pipeline

▸ Assets

▸ Code

▸ Ts

▸ Src

{ }Index { }Jobs { }Server { }Stages { }Types

▸ Tests

▸ Docs

MCapstone 12 — Video Understanding Pipeline (Scene, QA, Search)

▸ Outputs

MSkill Video Qa

▸ Mcp Server With Registry

▸ Assets

▸ Code

▸ Ts

▸ Src

{ }Index { }Protocol { }Tools { }Transport { }Types

▸ Tests

{ }Protocol.test

▸ Docs

MCapstone 13 — MCP Server with Registry and Governance

▸ Outputs

MSkill Mcp Server

▸ Speculative Decoding Server

▸ Assets

▸ Code

▸ Docs

MCapstone 14 — Speculative-Decoding Inference Server

▸ Outputs

MSkill Inference Server

▸ Constitutional Safety Harness

▸ Assets

▸ Code

▸ Docs

MCapstone 15 — Constitutional Safety Harness + Red-Team Range

▸ Outputs

MSkill Safety Harness

▸ Github Issue To Pr Agent

▸ Assets

▸ Code

▸ Ts

▸ Src

{ }Agent { }Index { }Router { }Server { }Types { }Verify

▸ Tests

▸ Docs

MCapstone 16 — GitHub Issue-to-PR Autonomous Agent

▸ Outputs

MSkill Issue To Pr

▸ Personal Ai Tutor

▸ Assets

▸ Code

▸ Ts

▸ Src

{ }Curriculum { }Index { }Mastery { }Repetition { }Server { }Types

▸ Tests

{ }Curriculum.test

▸ Docs

MCapstone 17 — Personal AI Tutor (Adaptive, Multimodal, with Memory)

▸ Outputs

MSkill Ai Tutor

▸ Agent Harness Loop Contract

▸ Code

▸ Tests

▸ Docs

MAgent Harness Loop Contract

▸ Tool Registry Schema Validation

▸ Code

▸ Tests

{ }Test Registry

▸ Docs

MTool Registry with Schema Validation

▸ Jsonrpc Stdio Transport

▸ Code

▸ Tests

{ }Test Transport

▸ Docs

MJSON-RPC 2.0 Over Newline-Delimited Stdio

▸ Function Call Dispatcher

▸ Code

▸ Tests

{ }Test Dispatcher

▸ Docs

MFunction Call Dispatcher

▸ Plan Execute Control Flow

▸ Code

▸ Tests

▸ Docs

MPlan-Execute Control Flow

▸ Verification Gates Observation Budget

▸ Code

▸ Tests

▸ Docs

MCapstone Lesson 25: Verification Gates and the Observation Budget

▸ Sandbox Runner Denylist

▸ Code

▸ Tests

▸ Docs

MCapstone Lesson 26: Sandbox Runner with Denylist and Path Jail

▸ Eval Harness Fixture Tasks

▸ Code

▸ Tasks

▸ Task 001 Fizzbuzz Offbyone

▸ Buggy

▸ Expected

▸ Task 002 Factorial Missing Return

▸ Buggy

▸ Expected

▸ Task 003 Error Message Typo

▸ Buggy

▸ Expected

▸ Task 004 Empty Reverse

▸ Buggy

▸ Expected

▸ Task 005 Linked List Traversal

▸ Buggy

▸ Expected

▸ Tests

▸ Docs

MCapstone Lesson 27: Eval Harness with Fixture Tasks

▸ Observability Otel Traces

▸ Code

▸ Tests

▸ Docs

MCapstone Lesson 28: Observability with OTel GenAI Spans and Prometheus Metrics

▸ End To End Coding Task Demo

▸ Code

▸ Fixture Repo

▸ Src

▸ Tests

▸ Tests

▸ Docs

MCapstone Lesson 29: End-to-End Coding Agent on the Harness

▸ Bpe Tokenizer From Scratch

▸ Code

▸ Tests

▸ Docs

MBPE Tokenizer From Scratch

▸ Tokenized Dataset Sliding Window

▸ Code

▸ Tests

{ }Test Dataset

▸ Docs

MTokenized Dataset with Sliding Window

▸ Token Positional Embeddings

▸ Code

▸ Tests

{ }Test Embeddings

▸ Docs

MToken and Positional Embeddings

▸ Multihead Self Attention

▸ Code

▸ Tests

{ }Test Attention

▸ Docs

MMulti-Head Self-Attention

▸ Transformer Block

▸ Code

▸ Tests

▸ Docs

MTransformer Block from Scratch

▸ Gpt Model Assembly

▸ Code

▸ Tests

▸ Docs

MGPT Model Assembly

▸ Training Loop Eval

▸ Code

▸ Tests

{ }Test Training

▸ Docs

MTraining Loop and Evaluation

▸ Outputs

▸ Loading Pretrained Weights

▸ Code

▸ Tests

▸ Docs

MLoading Pretrained Weights

▸ Classifier Finetuning

▸ Code

▸ Tests

▸ Docs

MCapstone Lesson 38: Classifier Fine-Tuning by Head Swap

▸ Instruction Tuning Sft

▸ Code

▸ Tests

▸ Docs

MCapstone Lesson 39: Instruction Tuning by Supervised Fine-Tuning

▸ Dpo From Scratch

▸ Code

▸ Tests

▸ Docs

MCapstone Lesson 40: Direct Preference Optimization from Scratch

▸ Eval Pipeline

▸ Code

{ }Gitignore { }Main

▸ Tests

▸ Docs

MCapstone Lesson 41: Full Evaluation Pipeline

▸ Large Corpus Downloader

▸ Code

▸ Tests

{ }Init { }Test Downloader

▸ Docs

MLarge Corpus Downloader

▸ Hdf5 Tokenized Corpus

▸ Code

▸ Tests

{ }Init { }Test Hdf5 Corpus

▸ Docs

MHDF5 Tokenized Corpus

▸ Cosine Lr Warmup

▸ Code

▸ Tests

{ }Init { }Test Schedule

▸ Docs

MCosine LR with Linear Warmup

▸ Gradient Clipping Amp

▸ Code

▸ Tests

{ }Init { }Test Amp

▸ Docs

MGradient Clipping and Mixed Precision

▸ Gradient Accumulation

▸ Code

{ }Main { }Test Main

▸ Docs

MGradient Accumulation

▸ Outputs

{ }Accum Curve MSkill Gradient Accumulation

▸ Checkpoint Save Resume

▸ Code

{ }Main { }Test Main

▸ Docs

MCheckpoint Save and Resume

▸ Outputs

{ }Resume Demo MSkill Checkpoint Save Resume

▸ Distributed Fsdp Ddp

▸ Code

{ }Main { }Test Main

▸ Docs

MDistributed Data Parallel and FSDP from Scratch

▸ Outputs

{ }Ddp Demo MSkill Distributed Fsdp Ddp

▸ Lm Eval Harness

▸ Code

{ }Main { }Test Main

▸ Docs

MLanguage Model Evaluation Harness

▸ Outputs

{ }Leaderboard MSkill Lm Eval Harness

▸ Tasks

{ }Arithmetic { }Code Exec { }Generation { }Multiple Choice { }Summary

▸ Hypothesis Generator

▸ Code

▸ Tests

{ }Test Generator

▸ Docs

MHypothesis Generator

▸ Literature Retrieval

▸ Code

▸ Tests

{ }Test Retrieval

▸ Docs

MLiterature Retrieval

▸ Experiment Runner

▸ Code

▸ Experiments

{ }Crashing Experiment { }Sparsity Experiment

▸ Tests

▸ Docs

MExperiment Runner

▸ Result Evaluator

▸ Code

▸ Tests

{ }Test Evaluator

▸ Docs

MResult Evaluator

▸ Paper Writer

▸ Code

▸ Tests

{ }Test Paper Writer

▸ Docs

▸ Critic Loop

▸ Code

▸ Tests

{ }Test Critic Loop

▸ Docs

▸ Iteration Scheduler

▸ Code

▸ Tests

{ }Test Scheduler

▸ Docs

MIteration Scheduler

▸ End To End Research Demo

▸ Code

▸ Tests

▸ Docs

MEnd-to-End Research Demo

Built with LearnaOS

← Courses Catalogue

#Phase 9: Reinforcement Learning

Agents that learn by doing. The foundation of RLHF.

See ROADMAP.md for the full lesson plan.