Menu
Sign In Search Podcasts Charts People & Topics Add Podcast API Blog Pricing
Podcast Image

The Startup Ideas Podcast

Building AI Agents (Clearly Explained)

08 Apr 2026

Transcription

Chapter 1: What advancements have been made in AI models recently?

0.031 - 1.793 Ras Mic

Ross Mike, welcome back to the pod.

0

1.833 - 3.955 Greg Isenberg

By the end of this episode, what are people going to learn?

0

Chapter 2: How do context windows influence AI agent performance?

4.336 - 14.507 Greg Isenberg

I hope I'm going to share some wisdom on how you can use the agents better. There's a lot of information going on right now. I disagree with most of it, and that's what we're going to talk about.

0

Chapter 3: What are skills in AI agents and why are they important?

14.527 - 20.653 Greg Isenberg

So at the end, whether you're building something, using an agent for some sort of work, you have the best output possible.

0

20.673 - 28.402 Ras Mic

And is this going to be a technical dive or, you know, non-technical person can... Anyone can watch this. There's going to be a lot of diagrams. That's all.

0
0

Chapter 4: How do you create effective skills for AI agents?

28.702 - 34.763 Ras Mic

You're going to make it clear to understand the concepts, right? Easy. Basics. Let's go.

0

42.674 - 55.434 Greg Isenberg

The first thing that I want to announce, previous episodes, we probably disagree with this point, but now what's true is the models are good. The models are exceptionally good. Opus 4.6 is amazing. GPT 5.4 is amazing.

0

Chapter 5: What tools and resources do you need to build AI projects?

55.754 - 70.116 Greg Isenberg

I know there's like two sets of camp where, especially when it comes to programming, people are like, oh, Opus is the better UI designer. GPT 5.4 is a better backend. Generally speaking, we've reached a point, we're not at AGI yet, where we reached a point where the models are good.

0

Chapter 6: How can you recursively improve AI skills over time?

70.096 - 94.351 Greg Isenberg

But context still matters. And you have the power to steer the models in a direction where you can get quality or you can get slop. And that's what I really want to talk about. But before we get into all that, and feel free to cut me off because this topic excites me, we need to learn how context works. And context is the model assembling information that it needs to execute an action.

0

94.912 - 106.111 Greg Isenberg

And the way the context is assembled, let's say in a coding agent, but really in any sort of agent, is there's this general system prompt, usually by the model provider. So for example, cloud code leaked recently.

0

Chapter 7: What strategies maximize token efficiency in AI agents?

106.612 - 122.703 Greg Isenberg

And one of the cool things that, especially as a developer, I got to do is I got to read the system prompt. So they have this general system prompt that guides the model on how to act, what to do, what not to do. The system prompt is very important. And then you have a lot of people have agent.md files or cloud.md files.

0

Chapter 8: What are the final thoughts on building productive AI workflows?

123.024 - 141.948 Greg Isenberg

Now I'm just going to say off rip, 95% of people don't need this. The reason being is, again, you have to assume that the models are already good, right? Now, imagine I told you, Greg, every time we're about to shoot a podcast, Greg, you need a microphone. You know you need a microphone, right? You've done this plenty of times, right?

0

142.008 - 165.196 Greg Isenberg

So if I'm building, like, let's say a website with cloud code, and I'm telling cloud code, this code base uses React, right? I don't need to because it has the code base in context. It can check the code, right? So there is this disparity where a lot of people are putting a lot of onus on the harness and the context building. And I'm low-key starting to strip things off.

0

165.596 - 174.247 Greg Isenberg

Like I'm going super, super minimal because, again, not to sound like an anthropic or open AI shill. Unfortunately, I have not been acquired. None of them are paying me.

0

175.268 - 185.901 Ras Mic

But the models are really, really good. Wait, so 95% of the time, I don't even need to bother with an agent MD file? You don't. Unless this is some sort of proprietary information.

0

185.941 - 204.407 Greg Isenberg

Yeah, what is the 5% of the time I should care about it? Proprietary information that may be specific to your company or some methodology that is specific to you that has to be referenced in every single conversation. Because the annoying part with an agent.md file is every time you go back and forth with the agent, it's added in the context, right?

204.387 - 231.846 Greg Isenberg

right the cool thing about skills and i'm going to talk about skills in a second the way skills are designed the skills are used in a way that's called progressive disclosure meaning when you have a skill file the entire thing is an additive context it's just the title and the description so the agent has the title and description in the context and when you let's say you have a notion report skill right and you tell your agent hey i want you to create a notion report and

231.826 - 249.611 Greg Isenberg

it's then going to check its context and be like, oh, I have this skill. Let me check out the entire document. So it's not in the context. What's in the context is the name and the description, but that's enough for the agent to be like, oh, this is a skill I need. Let me go use it, which is fantastic. I'm a skills maxi.

249.872 - 273.6 Greg Isenberg

And I'm going to show later in the episode, like how you craft the perfect skills. But with agent.md and cloud.md files, it's context being added at every turn. Right. So let's say you have like a thousand line file, claw.md. And let's say that's like 7000 tokens. You're spending 7000 tokens on every run. Now, do you need to? Most likely not. It probably should be a skill.

273.62 - 295.586 Greg Isenberg

But if you have some sort of company proprietary information or like there's something specific that you do that the model needs to know on every single turn, then you use it. The thing is, 95 percent of people don't have that. Right. So I'm not a fan unless that's the case. So and the reason being is we're wasting tokens. Right. It's in every single turn.

Comments

There are no comments yet.

Please log in to write the first comment.