Watch or read "An Opinionated Guide on the Best AI Coding Tools in 2025"

Learn about the current landscape of AI coding tools and their capabilities.

Build a prototype with Bolt

Read the blog post about Bolt.new and create your own prototype. Reply to the original post with your prototype link.

Create a full stack app with Replit

Watch the developer experience video and build your own full-stack application.

Install Cursor on your machine

Watch the tutorial and implement the Momentum Chrome extension following the blog post guide.

Install WindSurf Editor on your machine

Watch the demonstration video and implement the bike shop app on your local machine.

Prompt Engineering

Read and/or watch the videos on "The Prompt Report Parts 1 and 2" from Oxen.ai and read OpenAI's guidelines for text generation and prompting.

Retrieval Augmented Generation (RAG)

Read LangChain's overview on RAG, implement their tutorial on building a search engine over a PDF document, and read Cameron Wolfe's practitioner's guide.

Evaluation

Read about RAG evaluation metrics and learn about RAGAS framework for automated evaluation of RAG systems.

Overview

Watch Andrej Karpathy's video, "Deep Dive into LLMs like ChatGPT", which covers all the steps that go into making a modern chatbot like ChatGPT.

Understand the Transformer Network Architecture

Read Jay Alammar's "The Illustrated Transformer" blog post that visually explains the Transformer neural network architecture.

Pre-train to get a base model, Post-train via Supervised Fine Tuning (SFT) and Reinforcement Learning with Human Feedback (RLHF) to get a chatbot aligned with human preferences

Read Sebastian Raschka's "LLM Training: RLHF and its Alternatives" blog post. Read and watch the video on Oxen.ai's "Training Language Models to Follow Instructions (InstructGPT)" blog post.

Foundation — What Are Agents and Why Do They Matter?

Take Dr. Andrew Ng's "Agentic AI" short course on DeepLearning.AI. Learn agentic design patterns — reflection, tool use, planning, and multi-agent collaboration.

Building and Engineering Agents

Read Anthropic's "Building Effective Agents" guide and their follow-up article "Effective Context Engineering for AI Agents". Build AI agents and feed them the right context (prompts, memory, tool outputs, etc.).

Evaluating Agents

Read Anthropic's "Demystifying Evals for AI Agents". Build evaluation frameworks to measure and improve agent reliability.

Multi-Agent Systems in Practice

Read Anthropic's case study on building their multi-agent research system. Learn how multiple specialized agents can coordinate on a complex task.

Agent Protocols — Connecting Agents to Tools and Each Other

Read the intro to the Model Context Protocol (MCP) and take DeepLearning.AI's course on the Agent2Agent (A2A) protocol. MCP connects agents to tools; A2A connects agents to agents.

Foundation: What Is a Harness and Why Long-Running Agents Need One

Read Anthropic's "Effective Harnesses for Long Running Agents" and its companion "Harness Design for Long Running Apps." They explain why agents that run for minutes or hours, not seconds, need deliberate engineering for context compaction, error recovery, and state management.

Harness Design in Practice

Read OpenAI's "Harness Engineering: Leveraging Codex in an Agent-First World" for a practical look at building harnesses around coding agents in a real agent-first workflow.

Agentic Loops: Reliable Workflows That Learn Over Time

Every agent runs on a loop: observe, decide, act, repeat. "How to Solve Problems of Autonomous Agentic AI Workflows" covers common failure modes (drift, runaway loops, lost context) and how to keep a loop on track. LangChain's "Continual Learning for AI Agents" shows how the best loops learn from each iteration and improve with every run.

Putting It Together: An Always-On Agent You Can Message

Study the "Hermes Agent Masterclass" (architecture similar to OpenClaw): the harness and loop working together as an always-on agent that lives on a server, runs continuously, and reaches you over Telegram or Slack. Send it a task from your phone, and it works on its own and messages you back.