AI prompts
base on A curated list of Artificial Intelligence (AI) courses, books, video lectures and papers. # Awesome Artificial Intelligence
A curated collection of **must-use, actively maintained resources** for building and shipping AI systems.
Focus: **AI engineering** (RAG, agents, evals, guardrails, deploy) plus the best books, guides, papers, and a *carefully selected* set of tools.

---
## π Core Resources (Evergreen)
_The foundations β these will still be valuable five years from now, even if todayβs tools are gone._
### π Books
**Modern & Practical**
- [Designing Machine Learning Systems](https://www.oreilly.com/library/view/designing-machine-learning/9781098107956/) β Scalable, maintainable ML pipelines (Chip Huyen).
- [Generative Deep Learning (2nd Edition)](https://www.oreilly.com/library/view/generative-deep-learning/9781098134174/) β GANs, VAEs, diffusion models (David Foster).
- [AI Engineering](https://www.oreilly.com/library/view/ai-engineering/9781098166298/) β End-to-end AI product building (Chip Huyen).
- [100 Page Language Models Book](https://www.thelmbook.com/) β This book guides you through the evolution of language models, starting from machine learning fundamentals.
**Foundational**
- [Artificial Intelligence: A Modern Approach](https://aima.cs.berkeley.edu/) β Comprehensive AI theory (Russell & Norvig).
- [Deep Learning](https://www.deeplearningbook.org/) β Neural networks & architectures (Goodfellow, Bengio, Courville).
- [Reinforcement Learning: An Introduction (2nd Edition)](https://web.stanford.edu/class/psych209/Readings/SuttonBartoIPRLBook2ndEd.pdf) β RL fundamentals (Sutton & Barto).
---
### π AI Engineering
_Frameworks and design patterns for building robust, production-grade AI systems._
_Personal note: you don't need tons of frameworks β start with simple LLM calls and work up._
#### π Guides & Playbooks
- **[Building Effective Agents (Anthropic)](https://www.anthropic.com/engineering/building-effective-agents)** β β Patterns, pitfalls, and tradeoffs for designing AI agents.
- [OpenAI Agents Guide](https://cdn.openai.com/business-guides-and-resources/a-practical-guide-to-building-agents.pdf) β Practical guide on building agents
- [Google AI Agents Paper](https://www.kaggle.com/whitepaper-agents) - Practical guide to building AI agents from Google
- [Google Agents Companion Paper](https://www.kaggle.com/whitepaper-agent-companion) - Guide from Google
- [OpenAI Cookbook](https://cookbook.openai.com/) β Example code, recipes, and best practices for working with OpenAI APIs.
- [LLM Engineer Handbook](https://github.com/SylphAI-Inc/LLM-engineer-handbook) β A goldmine of useful links for AI engineers
#### π€ Frameworks
- [PocketFlow](https://the-pocket.github.io/PocketFlow/) β Extremely minimalist AI agent framework in just 100 lines of code. Fantastic way to learn.
- [Google ADK](https://google.github.io/adk-docs/) β Google's Agent Development Kit (Python, Java). Great local development experience + A2A + MCP.
- [Pydantic-AI](https://ai.pydantic.dev/) β Typed, structured LLM orchestration framework built on Pydantic models for safe, predictable outputs.
- [LangGraph](https://www.langchain.com/langgraph) β Build multi-agent workflows with stateful graphs on top of LangChain.
- [CrewAI](https://www.crewai.com/) β Agent orchestration with structured tasks and human-in-the-loop controls.
- [AutoGen](https://microsoft.github.io/autogen/) β Microsoftβs framework for multi-agent conversation and collaboration.
#### π¦ Retrieval-Augmented Generation (RAG)
- [LlamaIndex](https://www.llamaindex.ai/) β Data framework for ingesting, indexing, and querying private data with LLMs.
- [Haystack](https://haystack.deepset.ai/) β Open-source search/RAG framework with modular pipelines.
- [Docling](https://github.com/docling-project/docling) β Great library for ingesting any kind of document for RAG β
#### Evals
- [OpenAI Evals](https://github.com/openai/evals) β OpenAI's framework for writing evals
---
### π Landmark Papers
_Research that shaped modern AI β worth reading to understand the "why" behind todayβs architectures._
- [Attention Is All You Need](https://arxiv.org/abs/1706.03762) β Transformer architecture.
- [Scaling Laws for Neural Language Models](https://arxiv.org/abs/2001.08361) β Model/data/compute scaling.
- [Language Models are Few-Shot Learners](https://arxiv.org/abs/2005.14165) β GPT-3 capabilities.
- [Constitutional AI](https://arxiv.org/abs/2212.08073) β Safer model alignment.
---
## π Courses
_Learn from the best β structured content for every level._
**Beginner**
- [Google Generative AI Learning Path](https://www.cloudskillsboost.google/paths/118)
- [Hugging Face LLM Course](https://huggingface.co/learn/llm-course/chapter1/1)
- [Fast.ai β Practical Deep Learning](https://course.fast.ai/)
**Intermediate / Advanced**
- [Stanford CS324: Large Language Models](https://stanford-cs324.github.io/winter2022/)
- [Full Stack Deep Learning](https://fullstackdeeplearning.com/)
- [MIT 6.S191: Intro to Deep Learning](https://introtodeeplearning.com/)
**Focused**
- [DeepLearning.AI Short Courses](https://learn.deeplearning.ai/)
- [Google Deepmind| Introduction to Reinforcement Learning](https://www.youtube.com/playlist?list=PLqYmG7hTraZDM-OYHWgPebj2MfCFzFObQ)
- [Karpathyβs LLM Zero-to-Hero](https://www.youtube.com/playlist?list=PLAqhIrjkxbuWI23v9cThsA9GvCAUhRvKZ)
- [Neural Nets - Zero-to-Hero](https://www.youtube.com/playlist?list=PLAqhIrjkxbuWI23v9cThsA9GvCAUhRvKZ)
---
## π° Newsletters
_Stay current with AI developments without drowning in noise._
- [The Rundown AI](https://www.therundown.ai/)
- [AlphaSignal](https://alphasignal.ai/)
- [Superhuman AI](https://www.superhuman.ai/)
- [AI Engineer](https://newsletter.owainlewis.com)
## β‘ Tools
Tools for building and deploying AI applications.
### π¬ Models
- [ChatGPT](https://openai.com/chatgpt/overview/) β Best for general coding + reasoning.
- [Claude](https://www.anthropic.com/claude) β Best for long-context analysis and structured thinking.
- [Gemini](https://gemini.google.com/) β Best for Google ecosystem integration.
- [Perplexity](https://www.perplexity.ai/) β Best for quick research with live citations.
- [Cohere](https://cohere.com/) β Best for enterprise LLMs with strong retrieval-augmented generation APIs.
- [Mistral](https://mistral.ai/) β Best for lightweight, high-performance open-weight models.
- [Qwen](https://qwenlm.github.io/) β Best for multilingual and Chinese-first applications.
- [DeepSeek](https://deepseek.com/) β Best for efficient, cost-optimized large models with competitive reasoning.
### π¨βπ» Code & Developer Tools
- [Claude Code](https://www.anthropic.com/claude) β IDE extensions with long-context code edits.
- [GitHub Copilot](https://github.com/features/copilot) β In-IDE code completion, chat, and refactors.
- [Cursor](https://cursor.sh/) β LLM-powered IDE for multi-file edits and codebase-aware chat.
### π¨ Multimedia AI Tools
#### πΌ Image
- [ChatGPT-4o Image Generation](https://openai.com/chatgpt) β Integrated image creation with style control.
- [Midjourney](https://www.midjourney.com/) β Artistic and photorealistic images and video.
- [Adobe Firefly](https://www.adobe.com/sensei/generative-ai/firefly.html) β Integrated into Creative Cloud.
- [Ideogram](https://ideogram.ai/) β Precise, legible text in generated images.
- [Flux](https://blackforestlabs.ai/) β High-res, prompt-editable images.
#### π₯ Video
- [Kling](https://klingai.com/) β Cinematic, realistic video generation.
- [Google Veo 3](https://deepmind.google/technologies/veo/) β High-quality video with synchronized audio.
- [Runway](https://runwayml.com/) β Video editing + generation.
#### π Audio
- [ElevenLabs](https://elevenlabs.io/) β High-quality text-to-speech.
- [Suno](https://suno.ai/) β AI music from text prompts.
- [Aiva](https://www.aiva.ai/) β Music composition for media.
---
", Assign "at most 3 tags" to the expected json: {"id":"9223","tags":[]} "only from the tags list I provide: [{"id":77,"name":"3d"},{"id":89,"name":"agent"},{"id":17,"name":"ai"},{"id":54,"name":"algorithm"},{"id":24,"name":"api"},{"id":44,"name":"authentication"},{"id":3,"name":"aws"},{"id":27,"name":"backend"},{"id":60,"name":"benchmark"},{"id":72,"name":"best-practices"},{"id":39,"name":"bitcoin"},{"id":37,"name":"blockchain"},{"id":1,"name":"blog"},{"id":45,"name":"bundler"},{"id":58,"name":"cache"},{"id":21,"name":"chat"},{"id":49,"name":"cicd"},{"id":4,"name":"cli"},{"id":64,"name":"cloud-native"},{"id":48,"name":"cms"},{"id":61,"name":"compiler"},{"id":68,"name":"containerization"},{"id":92,"name":"crm"},{"id":34,"name":"data"},{"id":47,"name":"database"},{"id":8,"name":"declarative-gui "},{"id":9,"name":"deploy-tool"},{"id":53,"name":"desktop-app"},{"id":6,"name":"dev-exp-lib"},{"id":59,"name":"dev-tool"},{"id":13,"name":"ecommerce"},{"id":26,"name":"editor"},{"id":66,"name":"emulator"},{"id":62,"name":"filesystem"},{"id":80,"name":"finance"},{"id":15,"name":"firmware"},{"id":73,"name":"for-fun"},{"id":2,"name":"framework"},{"id":11,"name":"frontend"},{"id":22,"name":"game"},{"id":81,"name":"game-engine "},{"id":23,"name":"graphql"},{"id":84,"name":"gui"},{"id":91,"name":"http"},{"id":5,"name":"http-client"},{"id":51,"name":"iac"},{"id":30,"name":"ide"},{"id":78,"name":"iot"},{"id":40,"name":"json"},{"id":83,"name":"julian"},{"id":38,"name":"k8s"},{"id":31,"name":"language"},{"id":10,"name":"learning-resource"},{"id":33,"name":"lib"},{"id":41,"name":"linter"},{"id":28,"name":"lms"},{"id":16,"name":"logging"},{"id":76,"name":"low-code"},{"id":90,"name":"message-queue"},{"id":42,"name":"mobile-app"},{"id":18,"name":"monitoring"},{"id":36,"name":"networking"},{"id":7,"name":"node-version"},{"id":55,"name":"nosql"},{"id":57,"name":"observability"},{"id":46,"name":"orm"},{"id":52,"name":"os"},{"id":14,"name":"parser"},{"id":74,"name":"react"},{"id":82,"name":"real-time"},{"id":56,"name":"robot"},{"id":65,"name":"runtime"},{"id":32,"name":"sdk"},{"id":71,"name":"search"},{"id":63,"name":"secrets"},{"id":25,"name":"security"},{"id":85,"name":"server"},{"id":86,"name":"serverless"},{"id":70,"name":"storage"},{"id":75,"name":"system-design"},{"id":79,"name":"terminal"},{"id":29,"name":"testing"},{"id":12,"name":"ui"},{"id":50,"name":"ux"},{"id":88,"name":"video"},{"id":20,"name":"web-app"},{"id":35,"name":"web-server"},{"id":43,"name":"webassembly"},{"id":69,"name":"workflow"},{"id":87,"name":"yaml"}]" returns me the "expected json"