Stop Chatting With Claude. (Use This 1% Blueprint Instead)

Author: One Person Empire · Watch on YouTube

Video authored by the channel shown, not by IANIA; all rights belong to the creator. Transcript and summary generated automatically; the original-language content is preserved.

Original language: English

Original video: Stop Chatting With Claude. (Use This 1% Blueprint Instead) · Channel: One Person Empire · 15:09 · Watch on YouTube

Topics: AI agents, Task and workflow automation, Claude, Prompt and context engineering

Summary

The video presents Forge, a five-step system for getting better results from Claude by building a repeatable workflow instead of relying on clever prompts. It recommends giving Claude relevant background and examples, defining the desired outcome, letting Claude ask clarifying questions, generating and evaluating multiple drafts, and saving successful workflows for reuse. The speaker argues that more capable models raise the potential ceiling but that users need a system to make the most of them. Viewers are encouraged to try Forge on one recurring task.

Key points

Forge stands for Feed context, Outcome not task, Reverse interview, Generate then grade, and Export the win.
Use a Claude project to provide ongoing context about your business, audience, and what good work looks like.
Give Claude examples of your best work; examples can communicate style more effectively than adjectives, but should be carefully chosen.
Describe the desired outcome, audience, success criteria, and constraints rather than giving Claude only a task.
Ask Claude to interview you one question at a time before starting work, and tell it to flag vague or contradictory information.
Request three genuinely different versions, have Claude grade them against the stated criteria, then revise the winner.
Extended thinking can be enabled for the grading step to support a more considered critique.
Turn successful workflows into reusable project instructions or skills so you do not have to rebuild the process each time.
The speaker’s central argument is that better models increase the potential for strong results, while a good system helps users reach that potential.

Chapters

Start	Chapter	Summary
00:00	Why a system beats a magic prompt	The speaker contrasts generic AI output with work produced through a repeatable system and introduces Forge.
01:36	A better model needs a better brief	The video discusses Claude Opus 5.5 and argues that a model’s capabilities alone do not guarantee useful results.
03:07	F and O: context and outcomes	The first two Forge steps are to give Claude persistent context with curated examples and define the intended outcome and success criteria.
07:20	R: let Claude interview you	The speaker recommends asking Claude to surface missing information through a one-at-a-time reverse interview.
08:55	G and E: grade, improve, and save	The video explains how to generate and grade multiple versions, revise the strongest one, and save successful workflows for reuse.
13:07	The full Forge workflow and next steps	The speaker runs through all five steps, summarizes the system, and encourages viewers to test it on a weekly task.

Quotes

there is no magic prompt. — 00:32

Examples beat adjectives every time. — 04:41

Instead of trying to write the perfect prompt, you let Claude interview you first. — 07:20

The 1% never ask for one thing. They ask for options, and then they make Claude judge them. — 09:26

whenever a workflow actually works, when you get an output you love, you ask Claude one more question. — 11:32

Concepts and entities

Forge, Claude, Claude Opus 5.5, Anthropic, reverse interview, Extended Thinking, skill

Full transcript (original language)

00:00 Here’s something that bugged me for months. Two people open the exact same AI. Same model, same price, same blinking cursor. One of them gets a paragraph that sounds like a LinkedIn post written by a hostage. The other one gets a finished product, researched, structured, in their voice, ready to ship. And they got it in about the time it took the first person to type, “Make it better.” for the fourth time. Same tool, completely different results. And it’s not because the second

00:32 person knows some secret magic prompt. I promise you there is no magic prompt. I’ve looked. I’ve bought two of those 10,000 prompts PDFs. One of them was 9,000 prompts and 1,000 blank pages. The difference is that the second person isn’t prompting at all. They’re running a system. And with Anthropic dropping Claude Opus 5.5 this month, the gap between those two people just got a lot wider. Because

01:03 the smarter the model gets, the more it rewards people who know how to actually use it. And the more it quietly wastes on people who don’t. So, today, I’m giving you the system. I call it Forge. Five steps. Every single one of them you can use tonight on the free plan or paid. And by the end of this video, you’ll never type, “Write me a blog post about X.” again. Well, you might, but you’ll feel bad about it. Quick context, so we’re on the same page. On September 22nd, Anthropic

01:36 released Claude Opus 5.5. It’s the first model in their new 5.5 family. And there are two things about it that matter for you. Number one, Anthropic says it performs at the level of Claude Fable 5.1, their top-tier model, on most work. Fable is the one that was built for the heavy stuff, serious coding, serious knowledge work. Number two, it costs about 40% less to run than

02:06 Opus 5 on typical workloads. So, let me translate that into normal human language. You’re getting top-shelf performance at a lower price. That is like your gym announcing they’re cutting membership fees and also somehow the treadmills now work. Now, here’s the part nobody’s saying out loud. A more capable model does not automatically give you better results. It gives you a higher ceiling. Whether you reach that ceiling depends entirely on what you

02:36 give it to work with. Think of it like hiring. If you hire a genius and on day one you say, “Do marketing stuff.” you’re going to get generic marketing stuff. Very well-written generic marketing stuff, but generic. The genius didn’t fail. The briefed it. That’s what 99% of people are doing with Claude right now. They hired a genius and handed them a sticky note. Forge is how you write the brief. Let’s

03:07 go. F is feeded context. Here’s the uncomfortable truth. Most people start every single chat from scratch. New chat, blank slate. Hi Claude, I run a small business. Every single time. That’s like going to the same doctor for 5 years and every appointment she goes, “And you are?” The 1% do the opposite. They load context once and then every conversation starts already knowing who they are.

03:39 The easiest way to do that is projects. You create a project and inside it you put three things. One, [music] who you are. Your business, your role, what you sell, what you don’t do. Two, who it’s for, your audience. And I mean really describe them, not small business owners, more like solo founders, mostly 28 to 45, overwhelmed, allergic to jargon, already tried three productivity apps and quit all of them.

04:11 Three, and this is the one nobody does, what good looks like. Upload two or three examples of your best past work, your best email, your best script, and your best client proposal. >> [music] >> Because here’s the thing, you can spend an hour describing your writing style in adjectives, punchy but warm, professional but not stiff, and Claude will nod politely and give you something that sounds like a bank. Or you can just

04:41 show it three things you actually wrote, and it gets it instantly. Examples beat adjectives every time. [music] Quick story, when I first set this up, I uploaded my best scripts as examples, and then I read them again. And I realized two of them were, let’s say, not my best. So Claude started matching the energy of a girl who clearly filmed at 1:00 a.m. So lesson learned, curate your examples.

05:12 Claude will copy your worst habits with the same enthusiasm as the best ones. And if you have memory turned on, Claude can also carry preferences across conversations. So things like, I hate bullet point heavy answers, or always give me the short version first, stick without you repeating yourself. Worth two minutes to set up. Genuinely one of the highest return two minutes you’ll spend this year. O is outcome, not task. Most prompts

05:46 describe a task. Write an email, summarize this report, give me ideas for a video. The problem is that the task has no finish line. Claude has no idea what done looks like, so it guesses, and its guess is the safest, most average version of the thing. The 1% describe the outcome instead. What happens after this thing exists? Watch the difference. Task version, write an email to my list

06:17 about my new course. Outcome version, I need an email that gets people who’ve been on my list for over 6 months and have never bought anything to click through to the course page. They’ve seen a lot of launches from other people and they’re skeptical. Success means they feel like I’m talking to them specifically [music] and the email doesn’t feel like a launch at all. Under 200 words, no exclamation marks. I’m serious about the exclamation marks. Same request, but now Claude knows who’s

06:49 reading, what they’re feeling, what counts as a win, and what the constraints are. The second email is going to be dramatically better, and not because Claude got smarter between the two prompts, because you gave it a target. Here’s the simple version you can steal. Before you hit enter, answer three questions. Who is this for? What should they do or feel after? How will I know it’s worked? If you can’t answer those honestly, Claude can’t

07:20 either. And that’s not an AI problem. That was already a problem. The AI just made it visible. R is reverse interview. And if you only take one thing from this entire video, take this one. Instead of trying to write the perfect prompt, you let Claude interview you first. It looks like this. I want to mention your goal. Before you do anything, ask me the questions you’d need answered to do this

07:53 really well. Ask [music] them one at a time, and do not start the actual work until I say go. That’s it. [music] That’s the hack. And I know it sounds too simple, but think about what’s actually happening. You’re not good at predicting what Claude needs to know. Nobody is. You don’t know what you don’t know. But Claude is extremely good at spotting the gaps in a brief. So, you flip the direction. You stop guessing and let it pull the information

08:24 out of you. And the questions it asks are often better than the ones you think to answer. The first time I tried this, it asked me, “What’s the one thing your audience believes that’s stopping them from buying?” And I sat there for a full minute because I realized I had never actually thought about that for 3 years. It’s like hiring a consultant who charges nothing, has infinite patience, and doesn’t sigh when you give a bad answer, which honestly is more than I

08:55 can say for some consultants. Pro tip, for anything important, add this line at the end. “If anything I said is vague or contradicts itself, point it out.” Because sometimes the problem isn’t that you left information out, it’s that you told it two opposite things and it didn’t notice. G is generate then great. Here’s how most people work with AI. Ask for one thing, get one thing, and then

09:26 either accept it or start the “No, make it more like, you know, spiral.” The 1% never ask for one thing. They ask for options, and then they make Claude judge them. Step one, [music] give me three genuinely different versions of this, not the same idea reworded three times, three different angles. That last line matters. If you don’t say it, you’ll get the same email in three slightly different outfits. Step two,

09:57 and this is where it gets fun. Now grade each version against the success criteria I gave you. Be harsh. Tell me which one wins and what’s still weak about it. This works because of what we set up in step Oh, remember the success criteria? Now Claude has something real to measure against. It’s not grading on vibes, it’s grading on your definition of done. Step three, take the winner, fix the weaknesses you just named, and give me

10:29 the final version. Three steps, maybe two extra minutes, and the difference in quality is honestly kind of embarrassing, because it means for years I was accepting first drafts from a machine that will write a second draft instantly and for free and never once complained about it. I have been outworked by my own laziness. And with Opus 5.5 specifically, this step pays off even more. A more capable model is also a better critic. It’s

11:00 better at spotting what’s weak, which means the grade and fix loop gets you further per round than it used to. If you want to go one step further, turn on extended thinking for the grading step. Let it actually reason through the critique instead of rushing into an answer. It’s the difference between a teacher skimming your essay and one who actually reads it. And E, the last one is export the win. This is the step that turns the 1% into

11:32 the 0.1%. Here’s the thing about everything we just did. It’s great, but if you have to do it from scratch every time, you’ll stop doing it by Thursday. I know you will because I did. So, whenever a workflow actually works, when you get an output you love, you ask Claude one more question. That worked really well. Turn everything we just did, the context, the questions you asked, the criteria, the grading

12:03 into reusable instructions I can use next time. And now, you have a template. You paste that into your project instructions, or you save it as a skill if you’re using those. And next time, the whole forge process runs in one go. You’re not re-explaining yourself. You’re just running your system. That is the part that actually changes your week because every time you do this, you’re not just getting one good output. You’re building

12:35 a library of workflows that do exactly what you need in your voice to your standard. After a month, you have 10 of them. After 3 months, you basically have a small team. A small team that doesn’t need coffee, doesn’t need Slack, and has never once replied all to the whole company. That’s the whole idea behind this channel, by the way. One person running like a company. Not because you work harder, but because the stuff you figure out once keeps working for you after you

13:07 close the laptop. All right, let’s run the whole thing once fast so you can see it as one flow. F, I’m inside my project. It already knows my business, my audience, and it’s got my three best emails as examples. Oh, I describe the outcome, not the task. Who it’s for, what they should do, what done looks like. R, I tell it to interview me first. It asks four questions. One of them I

13:37 genuinely hadn’t thought about. Again, I’m starting to think that’s the point. G, three versions graded against my criteria, winner fixed. E, and I save the whole process as a reusable template, so next time this takes about 90 seconds. [music] So, forge. Feed it context, outcome not task, reverse interview, generate then grade, export the win. Here’s what I want you to actually walk

14:07 away with. The model is going to keep getting better. Opus 5.5 is better than what came before it, and whatever comes next will be better than this. But a better model doesn’t close the gap between people who use AI well and people who don’t. It widens it, because the ceiling keeps rising, and only the people with a system are climbing toward it. You don’t need to be technical to be on the right side of that gap. You just need to stop

14:38 treating Claude like a research bar and start treating it like the smartest new hire you’ve ever had. If you want to try it, pick one thing you do every week. Just one, and run it through forge tonight. Then come back and tell me in the comments what the reverse interview asked you. I read them, and I’m genuinely curious what questions it’s pulling out of people. >> [music] >> And if you want the next step, subscribe, because in the next video, I might show you how to take those saved

15:09 workflows and chain them together, so one request kicks off a whole process. I’ll see you there. >> Mhm.