<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
    <channel>
        <title>Engineering - Tag - Simi Studio</title>
        <link>/en/tags/engineering/</link>
        <description>Engineering - Tag - Simi Studio</description>
        <generator>Hugo -- gohugo.io</generator><language>en</language><managingEditor>simi@simi.studio (Simi)</managingEditor>
            <webMaster>simi@simi.studio (Simi)</webMaster><lastBuildDate>Fri, 20 Feb 2026 10:00:00 &#43;0800</lastBuildDate><atom:link href="/en/tags/engineering/" rel="self" type="application/rss+xml" /><item>
    <title>LLM Extended Thinking: Engineering Practices for &#34;Think Longer&#34;</title>
    <link>/en/posts/extended-thinking-llm/</link>
    <pubDate>Fri, 20 Feb 2026 10:00:00 &#43;0800</pubDate>
    <author>simi@simi.studio (Simi)</author>
    <guid>/en/posts/extended-thinking-llm/</guid>
    <description><![CDATA[Extended Thinking (thinking budget) is standard in 2026. But how to use it well, which scenarios are worth extra tokens—these are engineering problems.]]></description>
</item>
<item>
    <title>AI Context Management in Practice: RAG Is Not a Silver Bullet</title>
    <link>/en/posts/ai-context-management-guide/</link>
    <pubDate>Tue, 27 Jan 2026 14:00:00 &#43;0800</pubDate>
    <author>simi@simi.studio (Simi)</author>
    <guid>/en/posts/ai-context-management-guide/</guid>
    <description><![CDATA[When using AI for long texts or large codebases, RAG and long context each have strengths. This article clarifies when to use which and how to combine them.]]></description>
</item>
<item>
    <title>AI Agent Autonomy Levels: Is Your Agent L1 or L5</title>
    <link>/en/posts/ai-agent-autonomous-levels/</link>
    <pubDate>Sat, 03 Jan 2026 09:30:00 &#43;0800</pubDate>
    <author>simi@simi.studio (Simi)</author>
    <guid>/en/posts/ai-agent-autonomous-levels/</guid>
    <description><![CDATA[Everyone says AI Agent, but the word is diluted beyond meaning. This article uses a tiered framework to evaluate actual agent autonomy, from 'just chatting' to 'fully autonomous'.]]></description>
</item>
<item>
    <title>AI Application Testing Strategy: How to Test AI-Generated Code</title>
    <link>/en/posts/ai-testing-strategy/</link>
    <pubDate>Fri, 26 Dec 2025 09:25:00 &#43;0800</pubDate>
    <author>simi@simi.studio (Simi)</author>
    <guid>/en/posts/ai-testing-strategy/</guid>
    <description><![CDATA[Testing AI-generated code differs from regular code. This article explains AI code testing methodology.]]></description>
</item>
<item>
    <title>MCP After One Year: How I Integrated AI Agents into Real Workflows</title>
    <link>/en/posts/mcp-best-practices/</link>
    <pubDate>Sun, 21 Dec 2025 14:30:00 &#43;0800</pubDate>
    <author>simi@simi.studio (Simi)</author>
    <guid>/en/posts/mcp-best-practices/</guid>
    <description><![CDATA[MCP (Model Context Protocol) has been out for a year. This is my experience using MCP to build real workflows: pitfalls encountered, most valuable usage patterns, and scenarios where MCP is反而负担.]]></description>
</item>
<item>
    <title>Evaluating AI-Generated Code Quality: How to Judge if AI Wrote Good Code</title>
    <link>/en/posts/ai-code-quality-evaluation/</link>
    <pubDate>Sat, 15 Nov 2025 10:00:00 &#43;0800</pubDate>
    <author>simi@simi.studio (Simi)</author>
    <guid>/en/posts/ai-code-quality-evaluation/</guid>
    <description><![CDATA[After a year of using AI to write code, the biggest question remains: how do you judge if AI-generated code is good quality? This article gives a practical evaluation framework—not just 'review it,' but how to actually assess quality.]]></description>
</item>
<item>
    <title>AI-Assisted Code Review: Real Feedback After One Year</title>
    <link>/en/posts/ai-assisted-code-review/</link>
    <pubDate>Thu, 15 May 2025 10:00:00 &#43;0800</pubDate>
    <author>simi@simi.studio (Simi)</author>
    <guid>/en/posts/ai-assisted-code-review/</guid>
    <description><![CDATA[We've been using AI for Code Review for a year. Which scenarios does AI actually catch issues? Which does it completely miss? Real data, not theory.]]></description>
</item>
</channel>
</rss>
