Krish Naik · 45 min · intermediate · English

Step By Step Process To Build MultiModal RAG With Langchain(PDF And Images)

Latitude · 6 min · intermediate · English

LLM model comparison: choosing the right model for your use case

codebasics · 25 min · intermediate · English

OpenAI Api Crash Course For Beginners | Financial Data Extraction Tool Using OpenAI API

Amit Shekhar · 60 min · intermediate · English

AI Engineering Explained: LLM, RAG, MCP, Agent, Fine-Tuning, Quantization

Walks through the applied building blocks (RAG, agents, MCP, evaluation) you must reason about live in a prompt-system design / debugging round.

testRigor · 11 min · intermediate · English

Prompt Engineering Interview Questions - Part 1

Actual prompt-engineering interview questions to drill answers under interview framing.

Krish Naik · 18 min · intermediate · English

Prompt Engineering Vs RAG Vs Finetuning Explained Easily

Trade-offs talking points: prompt engineering vs RAG vs fine-tuning, explained simply.

Tina Huang · 20 min · intermediate · English

Google's 9 Hour AI Prompt Engineering Course In 20 Minutes

Compressed prompting fundamentals to rehearse core concepts out loud for interviews.

freeCodeCamp.org · 55 min · beginner · English

AI Engineer Roadmap – How to Learn AI in 2025

Maps the AI/prompt-engineering career path: which skills and roles (LLMs, RAG, fine-tuning, evaluation) teams hire for and how to get there.

asapfrontend · 11 min · beginner · English

3 Developer Portfolio Projects That Will Get You Hired

How to package a project into a recruiter-ready case study: live demo, clean repo, and a write-up of the problem, decisions, and results.

LangChain · 9 min · intermediate · English

LangSmith - Prompt Engineering with the Playground

Official walkthrough of storing, versioning, and reusing prompts via LangSmith Prompt Hub/Playground — packaging prompts as a documented, versioned library.

Krish Naik · 30 min · intermediate · English

End To End Text To SQL LLM App Along With Querying SQL Database Using Google Gemini Pro

End-to-end build of a portfolio-grade LLM feature grounded in a real database.

Promptfoo · 14 min · intermediate · English

Promptfoo Red Teaming: A beginner's guide to finding vulnerabilities in Your LLM Apps

Hands-on promptfoo walkthrough: install, run your first red-team scan, and read the results to find prompt failures.

IBM Technology · 10 min · intermediate · English

Securing AI Agents: How to Prevent Hidden Prompt Injection Attacks

Hardening system prompts and layering input/output guardrails and defense-in-depth against injection.

Microsoft Developer · 7 min · intermediate · English

Episode 4: Indirect Prompt Injection Explained | AI Red Teaming 101

Optional different angle: distinguishes direct vs indirect injection with a Microsoft AI Red Team walkthrough.

IBM Technology · 11 min · beginner · English

What Is a Prompt Injection Attack?

Clear primer on prompt injection — why LLMs can't separate instructions from data; the #1 OWASP LLM risk.

Comet · 18 min · intermediate · English

How to evaluate using LLM-as-a-Judge (Tutorial)

Using a model to grade outputs at scale for meaning, grounding, and style with a defined rubric.

echohive · 22 min · intermediate · English

Test Driven PROMPT Engineering: Using Promptfoo to COMPARE Prompts, LLMs, and Providers

Hands-on promptfoo: declarative configs, assertions, and side-by-side prompt/model comparison for regression testing.

Cole Medin · 25 min · beginner · English

Stop Vibe-Testing Your AI Agents: How to Actually Run Evals (in 25 Minutes)

Optional different angle: a fast, hands-on intro to replacing eyeballing with real evals.

Dave Ebbelaar · 34 min · intermediate · English

How to Systematically Setup LLM Evals (Metrics, Unit Tests, LLM-as-a-Judge)

Why moving from vibe checks to systematic, repeatable evals separates production AI from prototypes.

Tech With Tim · 30 min · intermediate · English

Model Context Protocol (MCP) Explained + Hands-on Tutorial

Optional hands-on: building/connecting an MCP server so an agent can actually use the tools.

Fireship · 9 min · beginner · English

I gave Claude root access to my server... Model Context Protocol explained

Fast, popular explainer of what MCP is and why it standardizes connecting agents to tools and data.

Data Centric · 24 min · intermediate · English

How To Build a React Agent in Python Step by Step!

Builds a ReAct Thought -> Action -> Observation loop in plain Python so the pattern is fully transparent.

Underfitted · 20 min · beginner · English

OpenAI Function Calling | LLM Tools Essentials

Optional hands-on: wiring OpenAI function calling to Python functions with valid JSON arguments.

IBM Technology · 12 min · intermediate · English

AI Tool Calling via Natural Language: LLMs, APIs & Docker in Action

How LLMs translate natural language into structured tool/function calls against real APIs.

AI Coffee Break with Letitia · 10 min · intermediate · English

Lost in the Middle: How Language Models use Long Context - Explained!

Walks through the Liu et al. paper showing U-shaped attention — models favor the start/end and under-attend the middle of long context.

Krish Naik · 36 min · intermediate · English

Retrieval Augmented Generation (RAG) with Langchain: A Complete Tutorial

Optional hands-on angle: building the prompt by injecting retrieved chunks + question into a RAG prompt template with LangChain.

IBM Technology · 7 min · beginner · English

What is Retrieval-Augmented Generation (RAG)?

Marina Danilevsky's canonical explainer: how retrieved documents are injected into the prompt to ground answers and cite sources.

IBM Technology · 11 min · intermediate · English

Context Engineering vs. Prompt Engineering: Smarter AI with RAG & Agents

Martin Keen frames prompt engineering as a subset of context engineering — designing everything the model sees (RAG, memory, agents).

DAIMTO Developer Tips · 8 min · intermediate · English

AI Prompt Pro: format output as CSV #generativeai #aiprompt

Concrete format-constraint demo: force the model to emit a specific shape (CSV).

Engineers Compass · 13 min · intermediate · English

Prompt Engineering Tutorial for Beginners | Class 4: Output Formatting & Structured Prompts

Structuring prompts and format constraints to steer consistent, exact output shape.

NetworkChuck · 24 min · intermediate · English

You SUCK at Prompting AI (Here's the secret)

Popular, high-quality walkthrough of structuring prompts with delimiters and tags to keep instructions and data separate.

Tim Warner · 14 min · intermediate · English

Structured LLM Prompting with XML

Hands-on use of XML tags and delimiters to cleanly separate instructions, context, and data into reusable templates.

ML Conference · 41 min · intermediate · English

Structured Outputs in OpenAI: Building Reliable JSON-Based AI Integrations

Optional deeper talk (MLcon) on JSON-schema enforcement and reliable structured outputs in real integrations.

Coding with Lewis · 14 min · intermediate · English

OpenAI Structured Output Tutorial (Responses API + JSON Schema)

Hands-on OpenAI Structured Outputs with a JSON schema so every response parses cleanly.

QWE AI Academy · 22 min · intermediate · English

AI Prompt Engineering Tutorial: ChatGPT System Prompts, Real Examples & API Integration

Optional different angle — system vs user message roles via the OpenAI API with concrete examples.

Anthropic · 24 min · intermediate · English

Anthropic just showed a 24-minute workshop on how to actually do prompts for Claude

Anthropic's own walkthrough of structuring prompts: system role, identity, rules and guardrails that persist across a conversation.

DeepLearningAI · 4 min · intermediate · English

Reasoning with OpenAI o1

Official DeepLearning.AI / OpenAI overview (taught by Colin Jarvis) on how o1 reasons internally and the simple-and-direct prompting principles that differ from standard CoT.

Packt · 9 min · intermediate · English

Prompt Engineering Masterclass | Self Consistency

Explains self-consistency: sampling the same CoT prompt multiple times and taking the majority answer to cut one-off reasoning errors.

Analytics Vidhya · 12 min · intermediate · English

Chain of Thought Prompting in Generative AI | Step-by-Step

Step-by-step walkthrough of CoT prompting and how 'think step by step' lifts accuracy on multi-step reasoning.

Engineering Academy Online · 13 min · intermediate · English

13 Iterative Prompting

Step-by-step iterative prompting: systematically refine and debug a prompt across successive attempts.

AI Foundations · 14 min · beginner · English

ChatGPT Prompt Engineering: Assigning Roles To ChatGPT! (Beginner's Guide)

How to assign roles/personas ('You are a...') to shift model behavior.

Adrian Twarog · 13 min · beginner · English

Master AI Prompting: Zero-Shot, Few-Shot & Chain of Thought Explained

Focused explainer contrasting zero-shot vs few-shot (in-context learning) with examples.

freeCodeCamp.org · 41 min · beginner · English

Prompt Engineering Tutorial – Master ChatGPT and LLM Responses

Full course; covers zero-shot prompting and writing clear instructions/best practices.

Anthropic · 25 min · beginner · English

Prompting 101 | Code w/ Claude

Anthropic's official walkthrough of prompt structure: role, instructions, context, examples, and constraints.

Matt Williams · 13 min · beginner · English

The Secret Controls for your LLM: Temperature, Top-K, Top-P, etc

Walks through temperature, top-k, top-p and friends — how each one shapes determinism vs creativity.

Analytics Vidhya · 9 min · beginner · English

What Are Tokens in LLM? | Tokenization Explained for AI Beginners

Short beginner explainer on what tokens are and why they drive cost and context limits.

Matt Pocock · 11 min · beginner · English

Most devs don't understand how LLM tokens work

Practical reasoning about how tokenization drives context limits and prompt cost.

3Blue1Brown · 27 min · beginner · English

But what is a GPT? Visual intro to transformers | Chapter 5, Deep Learning

Optional visual angle on the predict-sample-repeat loop behind every prompt.

Andrej Karpathy · 60 min · beginner · English

[1hr Talk] Intro to Large Language Models

The canonical mental model: an LLM is a next-token predictor, not a database lookup.