21 free resources on this topic. Everything here is free and hand-picked. You can also search within this topic.
Free guides on getting started with AI, prompting, choosing tools, and using AI at work. The collection explains practical AI topics in plain English.
A free-to-read collection of step-by-step AI workflow guides for Claude, ChatGPT, automation, and everyday work. The guide collection is separate from paid University courses; individual tools used in a guide may charge fees.
Sabrina Ramonov's step-by-step Substack tutorial that walks from simple AI questions up to a first autonomous AI agent. Five stages: Ask AI, Think with AI, Teach AI, Delegate to AI, and Automate with AI - each with copy-and-paste prompts, ending with an agent that connects to your tools and prepares a weekly report on its own. Cites PNC Research (July 2026) finding that 98% of US households still are not paying for AI in 2026.
Free mastery guides for ChatGPT, Claude, Gemini, Grok, Midjourney and other models, including a Claude Code starter guide, updated monthly. Guides are delivered by email after sign-up.
A June 2025 Wharton Generative AI Labs technical report by Lennart Meincke, Ethan Mollick, Lilach Mollick and Dan Shapiro. It tested "think step by step" prompting and found modest average gains with more variable answers for non-reasoning models, and only marginal gains for reasoning models despite 20–80% longer response times.
A free one-page PDF by James Maduk, dated 21 September 2026, on how to brief an AI assistant so it produces something usable. Gives an "Outcome Brief" of five questions to answer before handing over a job (what you want to make possible, who it is for and what is broken, what "done" looks like, what is off-limits or needs your approval, and the smallest version you could test), a three-question plan check for afterwards, and three worked before-and-after examples for client reviews, social posts and client onboarding.
Why I recommend it: The most useful line on it is the off-limits question — deciding in advance what never goes out without your sign-off is what keeps this safe for client work. Print it and keep it beside you the first few times; it turns "help me with client reviews" into a request a tool can actually deliver.
A free community-built study guide for Anthropic's Claude certification: what the exam covers, practice questions and the order to learn it in.
From the site: A collaborative AI workspace, built on your company context. Build and orchestrate agents right alongside your team
Why I recommend it: Community notes, not Anthropic's official material — check anything it claims about the exam against Anthropic's own page.
Official OpenAI guide for designing prompts for Realtime voice models, including gpt-realtime-2 and gpt-realtime-1.5. Covers role definition, guardrails, tool delegation and iterative testing.
Why I recommend it: Start here if you are building voice agents or want cleaner spoken-AI interactions. The guide recommends starting minimal and adding rules only for behaviors that fail in testing.
A curated, public Notion library of practical AI how-tos: tools, prompts, and step-by-step workflows organized so beginners can pick a task and follow it through.
Why I recommend it: A good starting shelf if AI still feels abstract — pick one workflow, run it end to end, then come back for the next.
A practical walkthrough of building a good slide deck with AI: what to hand the model, what to keep yourself, and how to avoid the generic deck AI produces by default.
Why I recommend it: Decks are where AI output looks laziest fastest. Use the prompts here for structure, then write the words yourself.
Anthropic's free learning hub for Claude: structured courses with video lessons and quizzes covering Claude.ai, Claude Code, Cowork, the API, and MCP, with completion badges.
Why I recommend it: A free, name-brand AI credential path. The Claude 101 course alone gives you something concrete to put under "skills" instead of vaguely claiming AI experience.
A two-page printable worksheet from Pilyoung Kim, Ph.D. for setting deliberate terms with AI: comparing warm, sycophantic, and machine-like responses, setting your own tone dials, turning them into a reusable custom-instructions prompt, deciding what goes to AI versus a person, and guarding your judgment against flattery.
Why I recommend it: Print it and actually fill it in. Section 5 — writing your own view down before you ask AI — is the single habit that keeps these tools from quietly making your decisions for you.
Created by Pilyoung Kim, Ph.D.
A three-page printable reference for Google Gemini: the PART prompt formula (Persona, Action, Reference, Tone), follow-up prompting, when to use Flash, Pro and Thinking models, saving your own context in settings, and worked sample prompts for Gemini inside Chrome, Gmail, Docs, Sheets, Slides and Drive. Includes a plain warning about Gemini being confidently wrong.
Why I recommend it: Print this and keep it next to you for a week. Most people get weak AI output because they skip the persona and the reference, and this one page fixes that faster than any course will. The limitations box at the bottom is the part to take seriously.
Created by CustomGuide
A browsable reference of design vocabulary — layout, type, and interface terms with live examples — useful for describing what you want when you brief a designer or an AI tool.
Why I recommend it: Half of getting good output from an AI design tool is knowing the right word for what is in your head. This is a free vocabulary cheat sheet for exactly that.
Anthropic's official collection of working code recipes and prompt patterns for building with Claude, covering retrieval, tool use, evaluation, and agent workflows.
Why I recommend it: The fastest way to go from "I use AI chat" to "I build with AI." Pick one recipe and ship a small tool with it this week.
Five-step walkthrough from Innovating with AI on creating a reusable Claude Skill so an assistant writes and works in your voice.
Why I recommend it: Details: build one skill around a task you repeat weekly — cover letters, client recaps, outreach — and you will feel the payoff immediately.
Free lessons on core AI concepts, prompting workflows, building and configuring AI agents, and applied ChatGPT use cases.
Why I recommend it: Practical rather than theoretical. Good for turning ChatGPT from a toy into part of your daily workflow.
About 10 hours of self-paced training on prompting, using AI tools at work, and responsible AI, with a free certificate.
Why I recommend it: The fastest credible line to add to your resume if you have zero formal AI training. Finish it in a weekend.
One-hour short course from Andrew Ng's team on the fundamentals of prompting.
Why I recommend it: Shortest high-signal course on this list. Do it before you write another AI prompt for your job search.
Associate Professor, Wharton School. Leading voice on the practical, everyday application of generative AI tools at work, author of 'Co-Intelligence.'
In plain terms: This LinkedIn profile shares research and practical insights on how artificial intelligence is changing everyday work. Follow his regular updates to track new AI tools and learn realistic ways to use them in your career.
Why I recommend it: The best source for how to actually use AI in your day-to-day work, with real prompts and tests.
Anthropic's free course teaching a practical framework for working with AI: delegation, description, discernment, and diligence. Good grounding before you use AI in job search, school, or client work.
In plain terms: This free online course teaches a practical framework for using artificial intelligence tools effectively and responsibly. You can practice prompting techniques, learn how to evaluate AI results, and earn a certificate of completion.
From the site: A free course from Anthropic on the 4D framework for working effectively and responsibly with AI: Delegation, Description, Discernment, and Diligence.
Why I recommend it: This is the fastest way to sound credible about AI in an interview. Take the course, then describe one task you redesigned with AI and what you checked before trusting the output.
