Resources: LLMs, Cursor, Streamlit and Prototyping
•1 min read
Product Management
Basics
Prompt Engineering & Guides
- OpenAI's guide on prompt engineering
- [1hr course] ChatGPT Prompt Engineering for Developers
- [1hr course] Building Systems with the OpenAI API
- [1hr course] LangChain Basics
- Guides and Capabilities in OpenAI's documentation
- Building effective agents (Anthropic)
- Pydantic is all you need: Jason Liu [Structured Outputs]
- Deep Dive into LLMs like ChatGPT
- Hugging Face Open-Source AI Cookbook
- Automatic Prompt Optimization - Cameron R. Wolfe, Ph.D.
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL
RAG
- [1hr course] LangChain: Chat with Your Data - DeepLearning.AI
- RAG from scratch
- RAG - basics and advanced
- A Practitioners Guide to Retrieval Augmented Generation (RAG)
- LLM Evals - building trust in your AI system
Evals
- Best Practices for LLM Evaluation of RAG Applications
- Your AI Product Needs Evals – Hamel's Blog
- Instrumenting & Evaluating LLMs
- Evaluating the Effectiveness of LLM-Evaluators (LLM-as-Judge)
- Using LLMs for Evaluation - Cameron R. Wolfe, Ph.D.
- Finetuning LLM Judges for Evaluation
Building AI Products
- LLM Guardrails: Trust, but Verify - Shreya Rajpal
- Making good AI products (UX for AI)
- Real ROI: Lessons from Enterprises - Raza Habib
- Iterating on LLM apps at scale - Ian Webster (Discord)
- Automatic Prompt Optimization - Cameron R. Wolfe
- PMing with o1 pro, v0, and DeepSeek-R1
- How to build the world's fastest voice bot - Kwindla Hultman Kramer
- What We Learned from a Year of Building with LLMs (Part I) – O'Reilly
- What We Learned from a Year of Building with LLMs (Part II) – O'Reilly
- Designing without Figma
Agents
- AI Agents 101
- Architecting and Testing Controllable Agents - Lance Martin
- AI Agents in LangGraph - DeepLearning.AI
Understanding LLMs
LLMs 101 by Karpathy:
- Let's build the GPT Tokenizer
- Let's build GPT: from scratch, in code, spelled out
- Let's reproduce GPT-2 (124M)
- Deep Dive into LLMs like ChatGPT
Go deeper:
- 3Blue1Brown: 1, 2, 3
- Large Language Models - LCS2
- Stanford CS224N: NLP with Deep Learning
- Low Level Technicals of LLMs - Daniel Han
LLM Inference
More Resources
- Short courses by deeplearning.ai
- Reasoning with o1 - DeepLearning.AI
- Large Multimodal Model Prompting with Gemini
- LLMs as Operating Systems: Agent Memory
- AI Engineer videos
- OpenAI DevDay 2024 - Swyx (realtime API + multi-agent)
- Planning red teaming for LLMs - Microsoft Learn
- Learnings on building - Eugene Yan
- Phi-4 Technical Report - Microsoft Research
People to Follow
- @jxnlco
- @sh_reya
- @hamelhusain
- @chipro
- @karpathy
- Cameron R. Wolfe (Substack)
- Jay Alammar
- Greg Isenberg (YouTube)
Prototyping & Building
- Lecture 4 - Building Product, Talking to Users, Growing (Adora Cheung)
- Lecture 7 - How to Build Products Users Love (Kevin Hale)
- Lecture 8 - How to Get Started, Doing Things that Don't Scale, Press
- Eric Migicovsky - How to Talk to Users
- The era of unbounded products: Designing for Multimodal IO - Ben Hylak
- [must watch] Pieter Levels: Programming, Viral AI Startups - Lex Fridman Podcast #440
- Tech Entrepreneurship Masterclass ft. Subhash, CTO @Dukaan
- AI Founder's Bitter Lesson. Chapter 1 - Lukas Petersson's blog