Thinking In Public – Issue #24 | I Run My Company With AI Agents. Here Is What That Actually Looks Like.

Thinking In Public – Issue #25 | Stop Losing Four Days to Every Presentation: Build the Deck and the Presenter View in One Evening With Claude Code

In this issue, I’m sharing the setup I use to prepare a training session from scratch. Not a review of presentation tools, and not a case for AI hype, but the actual folder, the two files inside it, and how the work gets done. This one is really about a shift in how I think about preparing to speak. Four days used to go into every session, three of them in Canva and a fourth spent typing the script into the little box under each slide. Now all of it comes together in one evening. I also get into something I haven’t seen many people talk about: everyone builds the slides, but nobody builds the second screen, the one you read from while you are standing in front of the room. So I built that one. The bigger point is this: the freedom is what made the difference. I had tried the AI presentation tools before and went back to Canva every time, because they handed me a template instead of what I asked for. This is the first thing that gave me both the speed and the design I wanted, and my own part of the work moved from building to directing. You don’t need to be a designer or a developer to run it. And if you teach or present for a living, it’s worth counting how many days a month go into decks. I packaged the whole setup into a free folder you can drop into your own Claude Code or other AI coding assistants. Download Present 👇 https://alperenzekigokmen.com/present [https://alperenzekigokmen.com/present] Hope you enjoy this one. — Alperen Zeki Gokmen [http://alperenzekigokmen.com/] Audio Disclaimer: This episode is made with AI voices. The AI hosts talk about the main ideas from my newsletter. Some small details may be different from the written text. For the most complete information, please read the full issue. This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit alperenzekigokmen.substack.com [https://alperenzekigokmen.substack.com?utm_medium=podcast&utm_campaign=CTA_1]

Thinking In Public – Issue #24 | I Run My Company With AI Agents. Here Is What That Actually Looks Like.

In this issue, I’m sharing the agent setup I use to run The Brutally Honest day to day. Not the theory behind AI agents, and not a tool comparison, but the actual folder structure, the connections, and how the work gets done. This one is really about a shift in how I think about getting things done. I connect agents to the tools we actually use, like Instantly, HubSpot, LinkedIn, and Fathom, and run multiple sessions in parallel instead of opening apps one by one. I also get into something I haven’t seen many people talk about: using a dedicated meetings folder where I give Claude Code and Codex a topic, step away, and let two models with different training push on each other’s reasoning until they reach a conclusion on their own. The bigger point is this: the infrastructure already works. You don’t need to be a developer, and you don’t need a complicated setup to start. And if you’re building products right now, it’s worth asking whether an AI agent can actually use what you’re making. Hope you enjoy this one. — Alperen Zeki Gokmen [http://alperenzekigokmen.com/] Audio Disclaimer: This episode is made with AI voices. The AI hosts talk about the main ideas from my newsletter. Some small details may be different from the written text. For the most complete information, please read the full issue. This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit alperenzekigokmen.substack.com [https://alperenzekigokmen.substack.com?utm_medium=podcast&utm_campaign=CTA_1]

Thinking In Public – Issue #23 | Vibe Coding Is Not Hard Because of Prompts

In this issue, I’m looking at vibe coding from a different angle. Not which tool to use, and not how to write the perfect prompt, but what actually matters before you even start building. This one is really about approach. Prompts matter far less than most people think. What matters more is being clear about the problem, staying patient when things break, testing what you build, and knowing how to work through friction without giving up too early. I also get into a common mistake I keep seeing: asking chatbots to write vibe coding prompts for you, then pasting those over-engineered instructions straight into the tool. The bigger point is simple: building is easier now, but good judgment still matters. And in many cases, the best place to start is not by trying to build something to sell, but by building something that saves you time first. Hope you enjoy this one. — Alperen Zeki Gokmen [http://alperenzekigokmen.com/] Audio Disclaimer: This episode is made with AI voices. The AI hosts talk about the main ideas from my newsletter. Some small details may be different from the written text. For the most complete information, please read the full issue. This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit alperenzekigokmen.substack.com [https://alperenzekigokmen.substack.com?utm_medium=podcast&utm_campaign=CTA_1]

Thinking In Public – Issue #22 | One Need One Tool The Practical AI Toolbox Map (Part 2)

In this issue, I continue the practical AI toolbox map with the second set of 25 needs, each paired with one tool or service that helps you get to a first usable result fast. This part leans more into presentations, research, productivity, sales workflows, and discovery. The point is the same: reduce the tool overload moment. Pick the closest need, pick the tool, then use any chatbot to turn your exact scenario into a simple first test and a short setup plan. If the first output is useful, you keep going. If it is not, you switch early instead of sinking hours. Hope you enjoy this one. Audio Disclaimer: This episode is made with AI voices. The AI hosts talk about the main ideas from my newsletter. Some small details may be different from the written text. For the most complete information, please read the full issue. This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit alperenzekigokmen.substack.com [https://alperenzekigokmen.substack.com?utm_medium=podcast&utm_campaign=CTA_1]

Thinking In Public – Issue #21 | One Need One Tool The Practical AI Toolbox Map (Part 1)

In this issue, I share a practical AI toolbox map: 25 real needs, each paired with one tool or service that helps you get to a first usable result fast. The goal is to remove the tool overload moment. You pick the closest need, pick the tool, then use any chatbot to turn your exact scenario into a simple first test and a short setup plan. If the first output is useful, you keep going. If it is not, you switch early instead of sinking hours. Hope you enjoy this one. Audio Disclaimer: This episode is made with AI voices. The AI hosts talk about the main ideas from my newsletter. Some small details may be different from the written text. For the most complete information, please read the full issue. This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit alperenzekigokmen.substack.com [https://alperenzekigokmen.substack.com?utm_medium=podcast&utm_campaign=CTA_1]