https://blog.margrop.net/en/tag/prompt-engineering/ Recent content in Prompt Engineering on Margrop Blog Hugo -- gohugo.io en-US Sun, 19 Jul 2026 18:30:00 +0800 https://blog.margrop.net/en/post/ai-token-context-window-sticky-notes/ Sun, 19 Jul 2026 18:30:00 +0800 https://blog.margrop.net/en/post/ai-token-context-window-sticky-notes/ <blockquote> <p><strong>The short version</strong></p> <p>AI often appears to have a bad memory because only a limited amount of material can be carried into the model for the current request. Think of a context window as a stack of sticky notes with finite capacity. New questions and tool outputs keep adding notes. Once the stack is full, the system must summarize, truncate, filter, or remove older notes. If a note is removed from the current context, the model may no longer be able to use it.</p> </blockquote> <p>Have you ever told an AI, “Use Python for every code example,” only to receive JavaScript fifteen turns later? Or supplied a long document that the model can summarize accurately at the beginning and end, but cannot answer about the important restriction buried in the middle?</p> <p>It is tempting to say that the AI “forgot.” A more precise explanation is this: <strong>the model can only see what fits inside the current context window, and seeing a piece of text does not guarantee that every part of it receives equal attention.</strong></p> <p>This article explains tokens and context windows without turning them into intimidating mathematics. The main analogy is a stack of sticky notes. We will look at what tokens are, how a request is assembled, why long conversations become unreliable, why agents fill their context quickly, and how to make AI forget less through simple information management.</p> https://blog.margrop.net/en/post/12-factor-agents-agent-principles/ Sat, 23 May 2026 14:50:00 +0800 https://blog.margrop.net/en/post/12-factor-agents-agent-principles/ <blockquote> <p><strong>The short version</strong></p> <p><code>12-Factor Agents</code> is not an installable agent framework, and it is not a Skill for Codex, Claude, Cursor, or any other agent runtime. It is better understood as a set of engineering principles for the AI era. When a system made from a large model, a tool list, and a while loop reaches the familiar 70% or 80% quality bar but refuses to become production-grade, these principles tell you where to look: prompts, context, structured outputs, state, human approval, error compaction, control flow, and recovery.</p> <p>The best part is that it does not romanticize agents. It says, in effect, that reliable agents are mostly software. The LLM is powerful, but it should live inside a system that is observable, interruptible, recoverable, auditable, and testable.</p> </blockquote> <p>All examples in this article use public projects, public links, and placeholders. No real server addresses, accounts, tokens, business configuration, or private network details are included. The figures are taken from the official <code>humanlayer/12-factor-agents</code> repository and are referenced under the project author&rsquo;s CC BY-SA 4.0 content license statement. Code license details should be checked in the upstream repository.</p>