<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:wfw="http://wellformedweb.org/CommentAPI/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:sy="http://purl.org/rss/1.0/modules/syndication/" xmlns:slash="http://purl.org/rss/1.0/modules/slash/" xmlns:memo="https://memo.d.foundation/ns/feed/1">
  <channel>
    <title>ai - Dwarves Memo</title>
    <atom:link href="https://memo.d.foundation/topics/ai-agents/tags/ai/rss.xml" rel="self" type="application/rss+xml" />
    <link>https://memo.d.foundation/topics/ai-agents/tags/ai</link>
    <description>The newest notes tagged ai on Dwarves Memo.</description>
    <lastBuildDate>Tue, 27 Oct 2026 00:00:00 GMT</lastBuildDate>
    <language>en-US</language>
    <sy:updatePeriod>hourly</sy:updatePeriod>
    <sy:updateFrequency>1</sy:updateFrequency>
    <item>
      <title>Agentic engineering: the series map and how to read it</title>
      <link>https://memo.d.foundation/agentic-engineering-series</link>
      <pubDate>Tue, 27 Oct 2026 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[tieubao]]></dc:creator>
      <description><![CDATA[A series on building agentic software for engineers who know the classic lifecycle, and how its pillars, deep dives and reading paths fit together.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/agentic-engineering-series</guid>
    </item>
    <item>
      <title>Owner agents, plain functions: where the model sits in our ops estate</title>
      <link>https://memo.d.foundation/owner-agents-and-functions</link>
      <pubDate>Sun, 25 Oct 2026 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[tieubao]]></dc:creator>
      <description><![CDATA[Give each domain one owner agent that reports back, keep the steps as plain functions, and add autonomy to a running platform one gated decision at a time.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/owner-agents-and-functions</guid>
    </item>
    <item>
      <title>No. 43: Tuan Dao on delegating to AI</title>
      <link>https://memo.d.foundation/once/tuan-dao/delegating-to-ai</link>
      <pubDate>Thu, 22 Oct 2026 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[tuanddd]]></dc:creator>
      <description><![CDATA[Tuan Dao, an engineer at Dwarves, on moving from pair programming with AI to delegating to it, and why human review is always the bottleneck.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/once/tuan-dao/delegating-to-ai</guid>
    </item>
    <item>
      <title>#5 Building is cheap now, getting heard is the hard part</title>
      <link>https://memo.d.foundation/wala-plot-ethan-phan</link>
      <pubDate>Sun, 18 Oct 2026 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[tieubao]]></dc:creator>
      <description><![CDATA[Han talks with Ethan Phan, co-founder and CTO of Plot, about reading a pivot signal, staying lean for 2.5 to 3 years, and running an AI-native engineering team where distribution, not building, is the bottleneck.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/wala-plot-ethan-phan</guid>
    </item>
    <item>
      <title>3,016 delegations to agents: the long briefs cost the most</title>
      <link>https://memo.d.foundation/communication-overhead</link>
      <pubDate>Sun, 18 Oct 2026 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[tieubao]]></dc:creator>
      <description><![CDATA[Median brief 289 words, median run 6.4 minutes, 14.5% needed a follow-up. What 24 days of Claude Code subagent logs say about briefing agents, and where a brief cost more than the work.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/communication-overhead</guid>
    </item>
    <item>
      <title>Harness engineering notes from a team running agents all day</title>
      <link>https://memo.d.foundation/harness-engineering-notes</link>
      <pubDate>Sun, 18 Oct 2026 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[tieubao]]></dc:creator>
      <description><![CDATA[Nine field notes on running coding agents in production at Dwarves: the harness around the model, how we check and guard it, what we put it to work on, and what it does to the pages we publish.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/harness-engineering-notes</guid>
    </item>
    <item>
      <title>We called ten technology arcs in June 2025. eight of the 60 experiments we planned got built.</title>
      <link>https://memo.d.foundation/navigate-ledger</link>
      <pubDate>Sun, 18 Oct 2026 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[tieubao]]></dc:creator>
      <description><![CDATA[Sixteen months after ten thesis notes, a scored ledger of what we built, which clients paid and what the market did, plus the five-step method that produced the calls.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/navigate-ledger</guid>
    </item>
    <item>
      <title>We stopped testing engineers on speed</title>
      <link>https://memo.d.foundation/capability-cliff</link>
      <pubDate>Sun, 18 Oct 2026 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[tieubao]]></dc:creator>
      <description><![CDATA[Dwarves cut the weight of timed algorithm problems in its technical interview from 60% to 15%. The dates, the weights, and the new hour.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/capability-cliff</guid>
    </item>
    <item>
      <title>Five layers to tune before you fork your agent</title>
      <link>https://memo.d.foundation/agent-tuning-layers</link>
      <pubDate>Thu, 08 Oct 2026 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[tieubao]]></dc:creator>
      <description><![CDATA[What makes AI agentic, how to split a deterministic core from an agentic edge, and the five layers you can tune without rebuilding the harness. Real numbers from circle and Hermes.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/agent-tuning-layers</guid>
    </item>
    <item>
      <title>What the Engelberg report got right about us</title>
      <link>https://memo.d.foundation/engelberg-report-audit</link>
      <pubDate>Mon, 07 Sep 2026 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[tieubao]]></dc:creator>
      <description><![CDATA[Thoughtworks published the findings of its second Future of Software Engineering retreat. Most of what the room converged on is what we have been learning and putting into practice at Dwarves. Here is each idea, what it means, the scene where it shows up here, and what comes next.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/engelberg-report-audit</guid>
    </item>
    <item>
      <title>Claude Code 2.1.259 turned our Read() deny rules into a Bash tripwire</title>
      <link>https://memo.d.foundation/claude-code-read-deny-bash-prompts</link>
      <pubDate>Thu, 03 Sep 2026 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[tieubao]]></dc:creator>
      <description><![CDATA[Bypass-mode sessions started stalling on 'a Read() deny rule is configured' prompts. What the harness now infers from a Bash command, why a CLAUDE.md rule couldn't stop it, and why we moved the secret-file guard from the deny list into a hook.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/claude-code-read-deny-bash-prompts</guid>
    </item>
    <item>
      <title>The debug loop: make the agent measure the browser before it touches the CSS</title>
      <link>https://memo.d.foundation/browser-loop-layout-debug</link>
      <pubDate>Thu, 03 Sep 2026 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[tieubao]]></dc:creator>
      <description><![CDATA[A repeatable loop for AI-driven UI debugging: name the metric, name the axis, drive a real browser over CDP, read the DOM into a table, kill theories, sweep the suspect, fix, re-run. With the probe code, the setup, the failure modes, and one worked case where three plausible CSS commits had changed nothing.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/browser-loop-layout-debug</guid>
    </item>
    <item>
      <title>Making our site AI-agent-ready, 50 to 93</title>
      <link>https://memo.d.foundation/agent-ready-website</link>
      <pubDate>Mon, 24 Aug 2026 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[tieubao]]></dc:creator>
      <description><![CDATA[We ran memo.d.foundation through is-agentic.com, read its rubric closely, and shipped the fixes that took the score from 50 to 93. Here is the rubric in full and what each fix actually did.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/agent-ready-website</guid>
    </item>
    <item>
      <title>Our publish step took 110 seconds, then 78. Our release tab took three tries.</title>
      <link>https://memo.d.foundation/deploy-pipeline-formula</link>
      <pubDate>Wed, 19 Aug 2026 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[tieubao]]></dc:creator>
      <description><![CDATA[Reading a CI log line by line cut memo's publish step from 110 to 78 seconds and exposed three silent bugs. Then agents started deploying all day, and the Releases tab needed three designs in 43 days.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/deploy-pipeline-formula</guid>
    </item>
    <item>
      <title>DeepSeek harness, dissected</title>
      <link>https://memo.d.foundation/deepseek-harness-architecture</link>
      <pubDate>Tue, 18 Aug 2026 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[tieubao]]></dc:creator>
      <description><![CDATA[An architecture read of dsh, DeepSeek's new agent harness: the plugin tree, the patch-layer boot, the log-first session model, and what it means for a Claude Code shop.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/deepseek-harness-architecture</guid>
    </item>
    <item>
      <title>What stays valuable when anyone can build anything</title>
      <link>https://memo.d.foundation/what-stays-valuable-when-anyone-can-build</link>
      <pubDate>Fri, 14 Aug 2026 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[tieubao]]></dc:creator>
      <description><![CDATA[As AI makes building cheap, value concentrates in judgment (inside) and trust (outside): the two inputs it cannot mass-produce. A lens on what to own in the AI era.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/what-stays-valuable-when-anyone-can-build</guid>
    </item>
    <item>
      <title>The tells</title>
      <link>https://memo.d.foundation/ai-writing-tells</link>
      <pubDate>Thu, 13 Aug 2026 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[tieubao]]></dc:creator>
      <description><![CDATA[AI writing gives itself away at the level of structure, not word choice. A field guide to the patterns, and the guideline change that bans them from our posts.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/ai-writing-tells</guid>
    </item>
    <item>
      <title>How knowledge work organizes itself</title>
      <link>https://memo.d.foundation/ai/how-knowledge-work-organizes-itself</link>
      <pubDate>Wed, 03 Sep 2025 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[monotykamary]]></dc:creator>
      <description><![CDATA[How societies naturally organize around different types of knowledge work; from those who apply compressed rules to those who derive new principles from scratch.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/ai/how-knowledge-work-organizes-itself</guid>
    </item>
    <item>
      <title>The five stages of learning</title>
      <link>https://memo.d.foundation/ai/the-five-stages-of-learning</link>
      <pubDate>Wed, 03 Sep 2025 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[monotykamary]]></dc:creator>
      <description><![CDATA[How human cognition and artificial intelligence both develop increasingly abstract representations, from simple stimulus-response patterns to deep hierarchical understanding.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/ai/the-five-stages-of-learning</guid>
    </item>
    <item>
      <title>E2b breakdown</title>
      <link>https://memo.d.foundation/breakdown/e2b</link>
      <pubDate>Wed, 27 Aug 2025 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[ngolapnguyen]]></dc:creator>
      <description><![CDATA[Technical analysis of E2B, a cloud infrastructure platform that runs AI-generated code in secure, isolated sandboxes using lightweight virtual machines that start in under 200ms.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/breakdown/e2b</guid>
    </item>
  </channel>
</rss>