<?xml version="1.0" encoding="utf-8"?>
<?xml-stylesheet href="https://bold.casa/feed_style.xsl" type="text/xsl"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en">
    <tabi:metadata xmlns:tabi="https://github.com/welpo/tabi">
        <tabi:base_url>https:&#x2F;&#x2F;bold.casa</tabi:base_url>
        <tabi:separator>
            •
        </tabi:separator>
        <tabi:about_feeds>This is a web feed, also known as an Atom feed. Subscribe by copying the URL from the address bar into your newsreader. Visit About Feeds to learn more and get started. It&#x27;s free.</tabi:about_feeds>
        <tabi:visit_the_site>Visit website</tabi:visit_the_site>
        <tabi:recent_posts>Recent posts</tabi:recent_posts>
        <tabi:last_updated_on>Updated on $DATE</tabi:last_updated_on>
        <tabi:default_theme>dark</tabi:default_theme>
        <tabi:post_listing_date>date</tabi:post_listing_date>
        <tabi:current_section>agentic</tabi:current_section>
    </tabi:metadata><link rel="extra-stylesheet" href="https://bold.casa/skins/monochrome.css?h=45c68d04a97602bbd53e" /><title>bold.casa - agentic</title>
        <subtitle>Workshop of John Rembold — builder, maker, inventor.</subtitle>
    <link href="https://bold.casa/tags/agentic/atom.xml" rel="self" type="application/atom+xml"/>
    <link href="https://bold.casa/tags/agentic/" rel="alternate" type="text/html"/>
    <generator uri="https://www.getzola.org/">Zola</generator><updated>2026-02-26T00:00:00+00:00</updated><id>https://bold.casa/tags/agentic/atom.xml</id><entry xml:lang="en">
        <title>Agent Proprioception: How Declarative Files Build the Self-Model</title>
        <published>2026-02-26T00:00:00+00:00</published>
        <updated>2026-02-26T00:00:00+00:00</updated>
        <author>
            <name>John Rembold</name>
        </author>
        <link rel="alternate" href="https://bold.casa/blog/agent-proprioception/" type="text/html"/>
        <id>https://bold.casa/blog/agent-proprioception/</id>
        <summary type="html">How agents build identity, continuity, and self-awareness through declarative files. The boot sequence, the compaction problem, file taxonomy, and why the files are the firmware.</summary>
        </entry><entry xml:lang="en">
        <title>Agent-to-Agent Affordances: Designing the Handoff</title>
        <published>2026-02-26T00:00:00+00:00</published>
        <updated>2026-02-26T00:00:00+00:00</updated>
        <author>
            <name>John Rembold</name>
        </author>
        <link rel="alternate" href="https://bold.casa/blog/agent-to-agent-affordances/" type="text/html"/>
        <id>https://bold.casa/blog/agent-to-agent-affordances/</id>
        <summary type="html">How agents delegate, coordinate, and hand off work to each other. Structured contracts, capability discovery, trust propagation, and why Conway&#x27;s Law applies to multi-agent systems.</summary>
        </entry><entry xml:lang="en">
        <title>Bimodal Affordances: Designing for Humans and Agents Simultaneously</title>
        <published>2026-02-26T00:00:00+00:00</published>
        <updated>2026-02-26T00:00:00+00:00</updated>
        <author>
            <name>John Rembold</name>
        </author>
        <link rel="alternate" href="https://bold.casa/blog/bimodal-affordances/" type="text/html"/>
        <id>https://bold.casa/blog/bimodal-affordances/</id>
        <summary type="html">How to design interfaces that serve both human understanding and agent consumption. The two-minds problem, layered information architecture, and why every surface now needs two readers.</summary>
        </entry><entry xml:lang="en">
        <title>Jidoka Trust Levels: When AI Agents Pull the Andon Cord</title>
        <published>2026-02-26T00:00:00+00:00</published>
        <updated>2026-02-26T00:00:00+00:00</updated>
        <author>
            <name>John Rembold</name>
        </author>
        <link rel="alternate" href="https://bold.casa/blog/jidoka-trust-levels/" type="text/html"/>
        <id>https://bold.casa/blog/jidoka-trust-levels/</id>
        <summary type="html">Applying Toyota&#x27;s jidoka principle to AI agent autonomy. A trust-level framework from full human control to full agent autonomy, with the critical insight: the agent must be able to stop itself.</summary>
        </entry><entry xml:lang="en">
        <title>Product Design in the Agentic Era</title>
        <published>2026-02-26T00:00:00+00:00</published>
        <updated>2026-02-26T00:00:00+00:00</updated>
        <author>
            <name>John Rembold</name>
        </author>
        <link rel="alternate" href="https://bold.casa/blog/product-design-agentic-era/" type="text/html"/>
        <id>https://bold.casa/blog/product-design-agentic-era/</id>
        <summary type="html">First principles for hybrid human-AI product development. Where design surfaces expand beyond pixels, why jidoka is the right model for AI trust, and what irreducible human work looks like when agents build faster than you can spec.</summary>
        </entry>
</feed>
