Open Textbook

Generative AI

5 Layers of an AI Agent: What Every Manager Needs to Know

19 min read

“Most people still think an AI agent is just ChatGPT with a good prompt.” That is the opening line of Sunil Ramlochan’s article “The AI Agent Stack Is Not a Prompt. It’s a Production System”, and the author calls this belief “a comforting myth.” The useful truth, he argues, is different: a real agent is closer to a small operating system for getting work done. It has a brain, hands, memory, rules, logs, recovery plans, and someone accountable when the agent does the wrong thing.

The article’s thesis fits in a single line: an agent is an entire stack. Reliability comes from the architecture around it, while the model itself – or a clever prompt – is just one ingredient. The picture is an engineering one, so let us approach it from the other side: what in this stack actually concerns the manager who does not write code but decides whether to put an agent to work.

Read more
5 Layers of an AI Agent: What Every Manager Needs to Know
Local LLMs for Managers: What You Can Actually Run at Home
20 min

Local LLMs for Managers: What You Can Actually Run at Home

Anyone who has spent enough time with ChatGPT or Claude eventually asks the question: can I run something similar right on my own laptop – without a subscription, without data leaving the machine, without depending on someone else’s servers?

In 2026, the answer is yes – but the caveats matter more than the answer.

This article is for people already using cloud LLMs who want to understand what local execution actually gives you, what hardware you need, and where expectations break down. No deep technical dive, but concrete numbers.

Make Weak Model Great Again: Can Prompting Fix a Weak AI Model?
6 min

Make Weak Model Great Again: Can Prompting Fix a Weak AI Model?

Every team has a ‘good enough’ model. Maybe it’s the one your company approved. Maybe it’s the one that runs locally because legal won’t let data leave the building. Maybe it’s the only option your country’s regulations allow.

In Russia, this is about to become very literal. In March 2026, the Ministry of Digital Development published a draft law on “trusted AI models.” If passed – enforcement is planned from September 2027 – government agencies and critical infrastructure will be limited to models from an approved registry. ChatGPT, Claude, and Gemini, which route data through foreign servers, could be restricted. Russian-made AI assistants would be pre-installed on devices by default.

The problem is that Russian models lag behind. In our study of 54 models, GigaChat scored 3.26 out of 5. GPT-5.4 scored 4.80. That’s a 32% gap.

If GigaChat is all Russian managers have, can smart prompting pull acceptable quality out of it?

Claude Code Costs $100/Month – OpenCode Does the Same Thing for Free
13 min

Claude Code Costs $100/Month – OpenCode Does the Same Thing for Free

In March 2026, Lenny Rachitsky published an article with a telling headline: “Everyone should be using Claude Code”. It went viral on LinkedIn and tech newsletters, picked up hundreds of thousands of views, and now every week a manager somewhere asks: how do I try this?

The answer is uncomfortable. The Anthropic Max subscription that unlocks Claude Code costs $100 per month. That’s $1,200 a year for a single tool – before you’ve even figured out whether it fits your workflow. And it locks you into a single vendor, a single model, and a pricing tier designed for power users, not for someone exploring whether AI agents are worth the investment.

There’s a direct alternative. OpenCode is an open-source project that does exactly the same thing, works with any model (including free ones), and takes 15 minutes to set up.

When AI Hurts Learning – and When It Doubles Results
10 min

When AI Hurts Learning – and When It Doubles Results

In March 2025 at SXSW EDU, strategic foresight advisor Sinead Bovell delivered a talk on AI and the future of education. No hype, no panic. But with two studies that change how you should think about AI’s role in learning.

First: a group of students who used ChatGPT without restrictions scored 17% worse than the control group working from a textbook. Second: a different group, where AI was deployed within a fully redesigned instructional system, outperformed a traditional lecture by a factor of two.

Same tool. Opposite outcomes. The difference is in the approach.

ClawCon, China, and $100B: OpenClaw Between Ecosystem and Bubble
12 min

ClawCon, China, and $100B: OpenClaw Between Ecosystem and Bubble

320,000 stars on GitHub. A physical conference in Manhattan. Government subsidies in Shenzhen. In six weeks, OpenClaw has gone from a repository with an interesting README to a geopolitical phenomenon discussed by Bernstein analysts, officials at China’s Ministry of Industry, and users on Xianyu posting consulting ads with the headline “will help you uninstall.”

This is the sixth part of the series. In the previous part, we recorded 265,000 stars, the creator joining OpenAI, the first enterprise deployments via Sundae Bar, and three new CVEs. That was 12 days ago.