Tutorials

Observability and Debugging AI Agents

December 22, 2025 · 55 min read

As your AI Agent grows more sophisticated, handling multi step plans, maintaining memory and using multiple tools, understanding what it’s doing and why becomes important. Without prooper observability, debugging agent failures feels like operating in the dark

---

Planning and Task Decomposition in AI Agents

December 15, 2025 · 27 min read

In the previous tutorial we built a code review agent that uses the ReAct pattern to reason about tasks, call tools and manage memory. However, our agent still handles tasks linearly; it takes one step at a time without a…

---

Agents That Think: Introducing the ReAct Pattern

November 19, 2025 · 12 min read

In our previous tutorials, we established the basic building blocks of an LLM agent. We implemented the observe,think,act loop, we added tool use and memory. Our agent can now read code, suggest improvements and remember past interactions.

---

Adding Memory to your Agent: Short-Term and Long-Term memory in practice

November 3, 2025 · 42 min read

Introduction In our previous tutorials, we built a code review agent that uses tools. But there’s a critical limitation:our agent has no memory between interactions. Every time we call think(), the agent starts fresh, with no knowledge of previous conversations…

---

Agents Tool Use: Adding Actions to your AI agent

November 3, 2025 · 15 min read

So far, our AI Code Assistant has learned how to think - it can read code and make intelligent suggestions.

---

From Prompts to Agents: Understanding the AI Agent Loop

November 3, 2025 · 4 min read

Introduction You have probably heard the term AI Agent, often mentioned, but not always clearly explained. In this tutorial series, we will demystify what AI agents really are.

---