Transcription since Substack’s transcription feature is failing brilliantly:
Hello, I’m Ahad Amdani. Welcome back to Generation AI. That’s G8N.AI, where I explore practical ways to build with artificial intelligence. I’m building in public, vibe coding custom AI tools, and sharing everything I learned along the way.
This is episode two, and I’m recording this less than 24 hours after episode 1 went live. That’s not because I’m some productivity machine. It’s because I’ve built a system that makes showing up easier than not showing up. Today, I want to talk about that system and why building frictionless workflows is the single most important thing you can do if you want to create content consistently.
Here’s something I want you to understand. I don’t feel like doing this tonight. I’m tired. I had a long day. Part of me wants to just skip it. Tell myself I’ll do it tomorrow. But here’s the thing. I have set up my process so that skipping feels worse than doing it.
That’s the mindset shift. When you’re relying on motivation, you lose. Motivation is unreliable. It shows up when you don’t need it and disappears when you do.
But a system? A system works whether you feel like it or not.
Right now, recording this audio content dump takes maybe 15 to 20 minutes. Tonight’s actually took 40 minutes. I’m literally just talking into my phone. That’s it. No fancy equipment, no perfect environment, just me rambling through the ideas I want to share.
Then the AI takes over. It transcribes. It organizes. It produces a script that I can refine. All of the tedious parts, the parts that I hate are handled. What’s left is the creative work, the part that I actually enjoy.
So when I think about skipping a day, I’m thinking 15 minutes of talking versus the failure of breaking my streak. The system made that math easy.
Let me walk you through exactly how this works. This is the same process I used for episode 1, and I’m validating it again right now with episode two.
Step one, audio content dump. I open the recorder app on my phone and I just talk. No script, no outline, just the ideas I want to cover in whatever order they come out. Sometimes it’s 10 minutes, sometimes it’s 40. Doesn’t matter. The goal is to capture raw content.
Step two, transcription. I drop that audio file into NotebookLM, Google’s AI Notebook tool. It generates a transcript. It’s not perfect, but it’s good enough for the next step.
Step three, script generation. I take that transcript and I paste it into my Claude project. I spent time building detailed instructions for how I want my podcast scripts formatted: tone, structure, pacing cues, everything. Claude transforms my rambling into a coherent script with sections, transitions, and delivery notes.
Step four, refinement. I read through the script. I adjust anything that doesn’t sound like me. I practice it out loud a few times. And this is where I spend my creative energy, not on the production logistics or on uh audio style or uh things that don’t really matter to me, right?
I care about the content. I care about making it appealing and I care about spreading this knowledge. I want to make sure that the message lands.
Step five, recording. Once I’m happy with the script, I record it properly. Right now, that’s still me reading into a microphone. Eventually, I’m planning to use an AI voice clone trained on my speech patterns. Either way, the recording is the easy part because all the thinking has already been done.
Step six, post-production. I run the audio through Podcastle AI to clean it up, reduce background noise, normalize levels, fix any obvious issues. Then it’s ready to publish.
Total time from idea to finished episode, 2 to 3 hours. And most of that is refinement, the work that I actually want to do. Right now, I’m still in the middle of this script, so I don’t know yet exactly how I’m going to make a bunch of changes.
For example, everything I’m saying right now isn’t scripted, but this is why I’m sharing this process in detail.
If you’re building a personal brand, if you’re trying to create content consistently, if you’re a solopreneur or a technical founder or someone who wants to share your expertise, you’ve probably struggled with the same problem I did. You know, you should be putting out content. You know it matters for your growth, but the friction is too high.
Writing a blog post from scratch, that’s a whole afternoon. Recording and editing a podcast the traditional way, that’s a whole day. And when it takes that long, you don’t do it. You push it off. You tell yourself, “Next week, this weekend, whatever.” Anything to get out of doing it right then.
But what if it took an hour? What if the hardest parts - the organization, the editing, the production - were handled by AI? Suddenly, consistency becomes possible. Suddenly, daily content isn’t crazy. It’s just a system.
The same philosophy applies to any high-value activity you’ve been avoiding because it’s tedious. Figure out what you hate about the process, then automate that part. Keep the creative work, delegate the rest.
Let me give you a concrete example of what’s possible when you apply this thinking to tool building. I built an app called Stack Coach AI. You can check it out at stack.g8n.ai. That’s stack.g8n.ai.
It’s a Substack content creation and coaching tool. You can draft posts, get AI feedback on your writing, generate images, transcribe audio, even get monetization strategy suggestions.
Here’s the thing. I built it in 3 hours. 3 hours start to finish. Front end. backend, deployment, custom domain, all of it. I used Gemini and Google AI Studio for the initial prototype. Then brought in Claude Code with Opus 4.5 to add the backend infrastructure. The tech stack includes React, TypeScript, SQLite, and it’s hosted on Vercel and Fly.io.
Now, I’m a senior developer with almost 20 years of experience. I knew the technologies involved. But even accounting for that, 3 hours to go from zero to deployed is insane. That’s the power of vibe coding with modern AI tools.
Is it production ready at scale? No, it’s a prototype. But prototypes become products. And if the prototype takes three hours, operationalizing it takes weeks, not months.
The point is the barrier to building custom solutions is collapsing. If there’s a tedious part of your process that you hate, you can probably automate it faster than you think.
I want to be clear about why I’m doing this. I believe most people are under-leveraged on AI. They’ve heard the hype. They might be scared of it. They’ve maybe played with ChatGPT a few times, but they’re not using these tools to fundamentally change how they work.
And I get it. There’s a learning curve. There are legitimate concerns about safety and bias and job displacement. And I’m not dismissing any of that.
But the technology is here. It’s getting better every month. And the people who learn to use it well, the citizen developers, the builders, the ones willing to experiment, they’re going to have a massive advantage. Not because they’re smarter, because they built better systems. Frictionless systems.
And that’s what I want to help with. Education, upskilling, showing what’s possible, building tools that demonstrate the approach, creating a community of people who are figuring this out together. If that resonates with you, stick around, subscribe, share this with someone who might benefit.
For episode three, I’m going to document something fun. I mentioned I’ve been talking to my business partner about updating some stale course content we have on our company site Explainly. He was skeptical that we could refresh it efficiently.
So I walked him through this exact podcast process, showed him episode one, explained the workflow, demonstrated the time savings. He’s convinced. We’re booking time to apply this approach to our educational content.
So episode three will cover that conversation, what objections came up, how I addressed them and what we’re planning to build together. It’s a real time case study in using AI to solve an actual business problem.
If you want me to vibe code a tool for you, something small, practical, something that solves a real pain point, drop a comment on this episode. Serious offer. I’ll pick one and build it live for a future episode.
That’s where we’ll leave it for today. Thank you for spending this time with me. I know there are infinite things competing for your attention.
And the fact that you chose to listen here? I don’t take that for granted.
Head over to g8n.ai for show notes and resources. That’s generation.ai and check out Stack Coach AI at stack.g8n.ai if you want to see what three hours of vibe coding looks like.
Until next time. Keep building, keep learning, keep asking good questions. Talk soon.
