The broad reference for classical AI, including search, reasoning, planning, learning, and robotics.

Sutton and Barto's foundational treatment of reinforcement learning concepts and algorithms.

A project-based introduction to building and deploying machine learning systems by Alexey Grigorev.

Scalable, maintainable machine learning systems by Chip Huyen.

Building applications with foundation models by Chip Huyen.

Implement transformers in PyTorch with Sebastian Raschka.

A visual and practical guide by Jay Alammar and Maarten Grootendorst.

LLMOps, fine-tuning, serving, and production workflows.

A concise, technical introduction by Andriy Burkov.

Mathematical foundations by Ian Goodfellow, Yoshua Bengio, and Aaron Courville.

A probability-grounded treatment by Christopher and Hugh Bishop.

Theory, intuition, and practical notebooks by Simon Prince.

The continuously updated NLP reference by Dan Jurafsky and James Martin.

A paid program for agentic coding and building, testing, and shipping production AI systems.

Transformers, fine-tuning, datasets, and modern NLP tooling.

The full lifecycle of building and shipping AI products.

A code-first introduction to deep learning.

Build neural networks and language models from first principles.

Build language models from data preparation through evaluation and deployment.

Deep learning foundations and applications.

An introductory path through generative AI concepts and Google Cloud tooling.

Focused courses on current generative AI engineering techniques.

An open course on designing, developing, deploying, and iterating on production ML systems.

Introduced the Transformer architecture.

Explored relationships between model performance, data, and compute.

Showed how model size and training data should scale together under a compute budget.

Demonstrated in-context learning at scale.

Combined parametric language models with external retrieval for knowledge-intensive tasks.

Introduced low-rank adaptation for parameter-efficient model fine-tuning.

Established the instruction tuning and RLHF recipe used by InstructGPT.

Combined reasoning traces with actions for tool-using language-model agents.

A method for training helpful and harmless AI assistants using written principles.

Reframed preference alignment as a simple classification objective without explicit reward modelling.

Anthropic's practical patterns and tradeoffs for agentic systems.

OpenAI's guide to models, tools, instructions, orchestration, and guardrails.

DeepSeek's official setup guides for integrating its models with coding agents including Claude Code, Codex, Cline,…

Code examples for structured outputs, tool use, retrieval, evals, and other LLM application patterns.

Techniques for defining success criteria, testing prompts, and improving model behaviour.

How to select, structure, and manage the context available to long-running agents.

Practical principles for building controllable LLM applications around deterministic software.

Risks and mitigations for developing and deploying generative AI applications.

The open specification for connecting AI applications to external tools, data sources, prompts, and interactive apps.

A vendor-neutral specification for agent discovery, task delegation, streaming, asynchronous updates, and…

Typed agent development built around Pydantic.

Low-level orchestration for long-running, stateful agents.

A small SDK for tools, handoffs, guardrails, tracing, and agent orchestration.

Google's framework for developing and evaluating agents.

Microsoft's successor to AutoGen and Semantic Kernel for agents and graph-based workflows.

Patterns for agents that make progress across multiple context windows and recover from failure.

Lifecycle, session, exception, and durable-execution patterns in the OpenAI Agents SDK.

Pause, inspect, approve, reject, and resume tool calls without losing agent state.

A concrete implementation of durable execution, retries, and human approval for an agent workflow.

Data ingestion, indexing, retrieval, and agent workflows.

Modular pipelines for retrieval and generative AI applications.

Document parsing and conversion for AI applications.

A practical method for building task suites, graders, transcripts, and evaluation harnesses.

An open-source framework and registry for evaluating language models and systems.

Test cases, assertions, model comparisons, and red-team checks for LLM applications.

Evaluation and experimentation for retrieval and generative AI applications.

Tracing, evaluation, prompt management, and metrics for LLM applications.

An inference and serving engine for language models.

A model gateway and unified interface for multiple model providers.

An open-source, workflow-first terminal coding agent with subagents, skills, sandboxed tools, and multiple model…

A terminal agent with hooks, subagents, skills, and repository-level instructions.

An open-source terminal agent with sandbox and approval controls.

An open-source terminal agent built around Gemini and extensible tools.

A terminal agent connected to Cursor's editor and cloud workflows.

An asynchronous agent that works from GitHub issues and opens pull requests.

An open-source pair programmer with Git integration and broad model support.

An open-source, provider-independent terminal agent with a client-server architecture.

An open-source platform for running software development agents locally or in the cloud.

An open-source coding agent available as an editor extension, CLI, and SDK.

Open-source coding agents for IDE and CI workflows with source-controlled configuration.

An open-source set of focused agent skills for designing, implementing, testing, reviewing, and shipping software…

OpenAI's field report on building software with coding agents, repository constraints, automated checks, and human…

A reference architecture that turns project work into isolated, observable coding-agent runs.

Production lessons on orchestrator-worker agents, parallel search, evaluation, and operational reliability.

is a developer-preview control plane for scheduling and coordinating Pi, Codex, and Claude Code workers across Git…