Prompting Path by Futureformed.io
A 30-day program

Go from AI-curious
to AI-fluent.

Prompting Path is a 30-day AI course: one 10-minute lesson and one real task a day. It takes you from your first prompt to building your own AI workflows. Not just faster with AI, better with it.

It's like a couch-to-5K for AI.

Find your starting point How it works
⏱️ 10 min/day 🎒 No prior experience 🆓 Free to start
Your progress 0%

0 of 30 days complete. Keep going, fluency compounds.

📅

One day at a time (or go fast)

About 10 minutes a day: a short lesson, then a real task. Pace it how you like, one a day or several at once.

🧭

Judgment, not just speed

Learn to steer AI, question it, and catch it when it's wrong, not just make it produce something.

🛠️

Build, don't watch

By Day 30 you've written prompts, built templates, and shipped a real AI workflow.

The full path

30 days, then beyond.

Prompting Path has 30 days in four weeks, plus a nine-module advanced track. Day 0 to Day 8 are free; Day 14 and Day 21 are free previews; the rest is a one-time £49 unlock. Read the full curriculum or the pricing.

Week 1: Foundations

How to talk to AI so it actually helps.

  1. Day 0: Pick your tool & meet the toolkit (10 min, free). Pick one AI assistant for the month, send your first message, and find the AI already inside the apps you use.
  2. Day 1: Your first great prompt (10 min, free). Write a prompt with the four ingredients that turn a vague request into a useful answer: role, task, context and format.
  3. Day 2: Take it for a spin (10 min, free). Play with AI for ten minutes, away from work, to learn where it shines and where it stumbles.
  4. Day 3: Show, don't tell (10 min, free). Use few-shot prompting: paste two or three real examples so the AI copies your style and structure.
  5. Day 4: Give it room to think (10 min, free). Ask the AI to reason step by step before it answers, for better decisions, plans and analysis.
  6. Day 5: When AI gets it wrong (10 min, free). Learn where AI makes things up, which facts to always check, and how web search and stronger models help.
  7. Day 6: Week 1 reflection (10 min, free). Look back on Week 1: what surprised you, what worked, and what you would now prompt differently.

Week 2: Context is king

The biggest lever for better answers, and how to push back.

  1. Day 7: Stuff the context window (10 min, free). Paste in the full thread or document, learn what tokens and context windows are, and watch the answers improve.
  2. Day 8: Long documents & summaries (10 min, free). Structure prompts for long documents, and ask them better questions than a plain summary.
  3. Day 9: Don't just ask, push back (10 min, full path). Start the judgment loop: form a rough view first, then work the AI's output in five modes.
  4. Day 10: System prompts & personas (10 min, full path). Write custom instructions that tell your AI who you are and how you want answers, in every chat.
  5. Day 11: Formats & the tone dial (10 min, full path). Set the format and tone of an answer precisely, and find the tone that sounds like you.
  6. Day 12: Build your first template (10 min, full path). Turn a task you do every week into a reusable prompt template you can find in five seconds.
  7. Day 13: Week 2 reflection (10 min, full path). Analyse the gap between your view and the AI's output: what it added, what it got wrong, and what only looks right.

Week 3: The right tool

Models, the AI in your everyday apps, files, images, memory.

  1. Day 14: Which model when (10 min, free preview). Learn the fast, balanced and heavy model tiers, pick your default, and know when to go heavy.
  2. Day 15: AI inside your everyday apps (10 min, full path). Use the AI built into Word, Excel, Outlook and Google's apps for formulas, drafts and summaries.
  3. Day 16: Projects, Artifacts & Canvas (10 min, full path). Set up your first Project to keep instructions, files and related chats together, and meet Artifacts and Canvas.
  4. Day 17: Files, images & voice (10 min, full path). Upload files, screenshots and photos, and use voice, for the tasks that are hard to type.
  5. Day 18: Image generation, with care (10 min, full path). Know when an AI image helps, when it can mislead, and what to check before you use one.
  6. Day 19: Memory & external brains (10 min, full path). Learn why AI forgets, and start an external brain of recap notes that you feed back in when needed.
  7. Day 20: Week 3 reflection (10 min, full path). Take stock of your AI setup: your tool, your default model, the app features you use, and what you skip.

Week 4: From chat to workflow

Build something small that saves you time every week.

  1. Day 21: The repeat-tasks audit (10 min, free preview). List your recurring tasks and rate them, to find the best candidate for your first AI workflow.
  2. Day 22: Pick and scope your build (10 min, full path). Choose one small task and write a one-page spec: input, output, rules, and what great looks like.
  3. Day 23: Build v1 (10 min, full path). Build your first working prompt from the spec, run it on a real, messy input, and get it 70% right.
  4. Day 24: Iterate to v2 (10 min, full path). Test your workflow on three real inputs, find where it fails, and fix it with examples and checks.
  5. Day 25: Make it reusable (10 min, full path). Save your workflow as a Project, Custom GPT, Gem or skill, so it runs the same way every time.
  6. Day 26: Connect a tool (if you can) (10 min, full path). Connect your AI to one tool you use, such as your calendar or email, and have it do a concrete job.
  7. Day 27: Use AI responsibly (10 min, full path). Spot trust drift, data leakage, bias and skill loss, and write your own three-rule AI policy.
  8. Day 28: Show your work (10 min, full path). Finish the judgment loop: share an AI-assisted piece with a short trail of what the AI did and what you changed.
  9. Day 29: Cross the finish line (10 min, full path). Reflect on thirty days, draw your map of where to trust AI, and claim your certificate.

Advanced track

Agents, your own toolkit, automation, dashboards, coding with AI, staying in control, efficiency, and your external brain.

  1. A1: Automate the routine (15 min, full path). Set up a scheduled AI task, such as a weekday morning brief, that runs without you.
  2. A2: Worked example: the book-club website (20 min, full path). Build and publish a one-page website with Claude, GitHub and Vercel, with no developer needed.
  3. A3: From artifacts to dashboards (15 min, full path). Combine artifacts into a live dashboard that answers the three questions you ask most about your data.
  4. A4: Build something real with Claude Code (20 min, full path). Describe a small piece of software in plain English, build it with Claude Code, then test it and fix it.
  5. A5: Your external brain, in practice (15 min, full path). Build a knowledge base and a Project loaded with your key documents, so every chat starts with your context.
  6. A6: How agents actually work (15 min, full path). Learn how an AI agent works in a loop with tools, and design two simple agents on paper.
  7. A7: Building your own toolkit (15 min, full path). Climb the ladder from saved prompts to custom assistants, connectors and skills, and build the next rung.
  8. A8: Staying in control as AI does more (15 min, full path). Sort AI tasks into three levels of human oversight, and audit the tools and connectors you have installed.
  9. A9: Why your AI session runs out of steam (15 min, full path). Learn why long chats slow down and hit limits sooner, and the habits that keep your sessions sharp.
FAQ

Frequently asked.

How is this different from other AI tutorials?
Most AI "tutorials" are 90-minute videos teaching one tool. Prompting Path is the opposite: thirty 10-minute days, tool-agnostic, ending with a small AI workflow you actually ship. And it teaches judgment, knowing when AI is wrong, not just prompting. The aim is to build a daily habit, not to watch.
Who made this?
Liam D, Founder and Principal Advisor at Futureformed, an AI advisory practice helping organisations put humans in the loop on real AI deployments.
Why should I trust them?
Futureformed advises organisations on live AI deployments, workshops, audits, build engagements. This curriculum is the same shape used with paying clients, distilled down. If you want it taken into your team or organisation, that's what Futureformed does.
How much does it cost?
The first nine days, Day 0 to Day 8, are free. All we ask for is an email address, no card details. The rest of the path, 21 more days plus the nine advanced modules, is a single one-time payment. Not a subscription: pay once, keep it forever, future updates included. The current price is an early sign-up offer while the path is new, it won't stay this low, but whatever you pay is the only payment you'll ever make. There's a promo code box at checkout for when we run offers. And the free days will stay free, if they help you, forward them to someone who'd benefit.
Why do you ask for my email?
Two reasons, both boring: so we know roughly who's walking the path, and so we can tell you about big updates to the curriculum (which you keep for free if you've unlocked). That's it. No spam, no selling your address, and you only enter it once per browser.
I paid on another device. How do I get access here?
Sign in (header button) with the same email you used at checkout and the unlock follows you automatically. Access codes from your purchase confirmation still work too: click "Restore access" in the footer and enter it once while signed in, and it's attached to your account for good.
Do I need to code?
No. Not a single day in the 30 requires code. The advanced track has one optional module on building with Claude Code, and even that assumes you've never written a line.
Can I do this with my kids, or as a family?
Lots of people do. The days are short, plain-English and screen-light, which makes this a good way to teach a teenager good habits rather than letting AI become "a faster Google". A nice rhythm: everyone does the short days solo, then picks one task to do together at the dinner table once a week.
Do I need a paid AI chatbot subscription?
No. The free tiers of Claude, ChatGPT, Gemini or Microsoft Copilot are enough for every day. Paid plans add longer files and access to the latest models, but they're nice-to-have, not required.
Does this work on Windows?
Yes. Everything here is browser-based. Mac, Windows, Linux, ChromeOS, wherever you can open Claude, ChatGPT, Gemini or Copilot in a browser, you can do this. If you're on Windows, Copilot is likely already built into your taskbar.
Why am I using those tools?
Claude, ChatGPT, Gemini and Microsoft Copilot are the leading general-purpose AI assistants in 2026. Copilot is built on OpenAI's models, so if your workplace gives you that, you're in good hands. Pick the one you already have, or try a couple on a free tier. The curriculum is deliberately tool-agnostic, the goal is fluency you can carry to whichever model wins in the long run.
Are there any other tools you recommend?
After Week 4, two genuinely useful additions: a notes tool like Obsidian or Notion for your growing prompt library, and a no-code automation tool like n8n or Zapier once you reach the advanced track. Beyond those, it's shiny-object territory, resist.
Does my progress sync across devices?
Yes. Tap "Sign in" in the header, we email you a link (no password), and from then on your progress, your unlock and your certificate follow you between laptop, tablet and phone. Not signed in? Progress still saves to the browser you're using.