<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Learn — Felesh</title><description>Learn</description><link>https://blog.felesh.ai/</link><item><title>From LLMs to agents: the complete journey</title><link>https://blog.felesh.ai/en/learn/llms-to-agents/from-llms-to-agents/</link><guid isPermaLink="true">https://blog.felesh.ai/en/learn/llms-to-agents/from-llms-to-agents/</guid><description>A language model, at heart, just guesses the next word. Here&apos;s how that simple guess becomes an agent once you add tools, memory, and planning — and where you actually need one.</description><pubDate>Sun, 21 Jun 2026 00:00:00 GMT</pubDate></item><item><title>How agents remember: memory and knowledge representation</title><link>https://blog.felesh.ai/en/learn/llms-to-agents/how-agents-remember/</link><guid isPermaLink="true">https://blog.felesh.ai/en/learn/llms-to-agents/how-agents-remember/</guid><description>A language model has no memory of its own and begins each conversation from scratch. What gives an agent memory is the layers built around the model.</description><pubDate>Sun, 21 Jun 2026 00:00:00 GMT</pubDate></item><item><title>How an AI agent thinks</title><link>https://blog.felesh.ai/en/learn/llms-to-agents/how-agents-think/</link><guid isPermaLink="true">https://blog.felesh.ai/en/learn/llms-to-agents/how-agents-think/</guid><description>An agent takes a goal, reasons, acts, and observes the result — repeating that loop until it&apos;s done. A simple mental model for how agents reason and decide.</description><pubDate>Sun, 21 Jun 2026 00:00:00 GMT</pubDate></item><item><title>Prompt engineering from zero: write a formal letter, not a text message</title><link>https://blog.felesh.ai/en/learn/llms-to-agents/prompt-engineering-from-zero/</link><guid isPermaLink="true">https://blog.felesh.ai/en/learn/llms-to-agents/prompt-engineering-from-zero/</guid><description>A language model can&apos;t read your mind. Everything you&apos;d take for granted in a casual chat has to be stated outright in the prompt — the six components that make a good one, and the five mistakes beginners make.</description><pubDate>Sun, 21 Jun 2026 00:00:00 GMT</pubDate></item><item><title>One agent or many? When each one fits</title><link>https://blog.felesh.ai/en/learn/llms-to-agents/single-agent-vs-multi-agent/</link><guid isPermaLink="true">https://blog.felesh.ai/en/learn/llms-to-agents/single-agent-vs-multi-agent/</guid><description>Sometimes a single agent is the best answer, and sometimes the work should be split across several. The deciding factor is the complexity of the task, not how advanced the architecture looks.</description><pubDate>Sun, 21 Jun 2026 00:00:00 GMT</pubDate></item></channel></rss>