<?xml version="1.0" encoding="utf-8"?>
<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/">
    <channel>
        <title>Pathmode Blog | The Builder's Log</title>
        <link>https://pathmode.io</link>
        <description>Design operations, engineering culture, and the future of building products.</description>
        <lastBuildDate>Sun, 31 May 2026 09:08:58 GMT</lastBuildDate>
        <docs>https://validator.w3.org/feed/docs/rss2.html</docs>
        <generator>Feed for Node.js</generator>
        <language>en</language>
        <image>
            <title>Pathmode Blog | The Builder's Log</title>
            <url>https://pathmode.io/images/pathmode-icon-v2.png</url>
            <link>https://pathmode.io</link>
        </image>
        <copyright>All rights reserved 2026, Pathmode Inc.</copyright>
        <item>
            <title><![CDATA[Context Rot Starts Upstream]]></title>
            <link>https://pathmode.io/blog/context-rot-starts-upstream</link>
            <guid isPermaLink="false">https://pathmode.io/blog/context-rot-starts-upstream</guid>
            <pubDate>Sun, 24 May 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Anthropic gave the runtime problem a name last fall: context rot. The runtime fix is curation. The upstream fix is intent, and most teams are still skipping that layer entirely.]]></description>
            <content:encoded><![CDATA[Anthropic gave the runtime problem a name last fall: context rot. The runtime fix is curation. The upstream fix is intent, and most teams are still skipping that layer entirely.]]></content:encoded>
            <author>hello@pathmode.io (Janne Lammi)</author>
        </item>
        <item>
            <title><![CDATA[Intent vs. Issues]]></title>
            <link>https://pathmode.io/blog/intent-vs-issues</link>
            <guid isPermaLink="false">https://pathmode.io/blog/intent-vs-issues</guid>
            <pubDate>Wed, 20 May 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Execution is becoming abundant. Intent is becoming the scarce input. On the layer above the issue.]]></description>
            <content:encoded><![CDATA[Execution is becoming abundant. Intent is becoming the scarce input. On the layer above the issue.]]></content:encoded>
            <author>hello@pathmode.io (Janne Lammi)</author>
        </item>
        <item>
            <title><![CDATA[Input Factories]]></title>
            <link>https://pathmode.io/blog/input-factories</link>
            <guid isPermaLink="false">https://pathmode.io/blog/input-factories</guid>
            <pubDate>Tue, 19 May 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Everyone is building agent factories. The leverage is upstream — in the inputs the agents read before the build. Most teams are scaling their ambiguity, faster.]]></description>
            <content:encoded><![CDATA[Everyone is building agent factories. The leverage is upstream — in the inputs the agents read before the build. Most teams are scaling their ambiguity, faster.]]></content:encoded>
            <author>hello@pathmode.io (Janne Lammi)</author>
        </item>
        <item>
            <title><![CDATA[Anthropic and OpenAI Are Pointing at the Same Gap in Agentic Coding]]></title>
            <link>https://pathmode.io/blog/anthropic-openai-same-gap</link>
            <guid isPermaLink="false">https://pathmode.io/blog/anthropic-openai-same-gap</guid>
            <pubDate>Mon, 11 May 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Anthropic names the trust gap. OpenAI expands the execution surface. Two different motions, one shared pressure: agentic coding is becoming operational, but the upstream definition of what should happen and how success is verified is still too thin.]]></description>
            <content:encoded><![CDATA[Anthropic names the trust gap. OpenAI expands the execution surface. Two different motions, one shared pressure: agentic coding is becoming operational, but the upstream definition of what should happen and how success is verified is still too thin.]]></content:encoded>
            <author>hello@pathmode.io (Janne Lammi)</author>
        </item>
        <item>
            <title><![CDATA[Anthropic Just Made Specs Load-Bearing]]></title>
            <link>https://pathmode.io/blog/anthropic-just-made-specs-load-bearing</link>
            <guid isPermaLink="false">https://pathmode.io/blog/anthropic-just-made-specs-load-bearing</guid>
            <pubDate>Wed, 06 May 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Anthropic's new Outcomes feature turns success criteria into the agent's contract. That makes specs — not prompts — the artifact your team can't fake.]]></description>
            <content:encoded><![CDATA[Anthropic's new Outcomes feature turns success criteria into the agent's contract. That makes specs — not prompts — the artifact your team can't fake.]]></content:encoded>
            <author>hello@pathmode.io (Janne Lammi)</author>
        </item>
        <item>
            <title><![CDATA[The Three-Person Team]]></title>
            <link>https://pathmode.io/blog/the-three-person-team</link>
            <guid isPermaLink="false">https://pathmode.io/blog/the-three-person-team</guid>
            <pubDate>Tue, 05 May 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Software teams have been coordination problems for so long we forgot they had to be. As AI absorbs the middle of the work, a different shape is starting to emerge.]]></description>
            <content:encoded><![CDATA[Software teams have been coordination problems for so long we forgot they had to be. As AI absorbs the middle of the work, a different shape is starting to emerge.]]></content:encoded>
            <author>hello@pathmode.io (Janne Lammi)</author>
        </item>
        <item>
            <title><![CDATA[Linear Says Issue Tracking Is Dead. They're Right About Half of It.]]></title>
            <link>https://pathmode.io/blog/linear-issue-tracking-half-right</link>
            <guid isPermaLink="false">https://pathmode.io/blog/linear-issue-tracking-half-right</guid>
            <pubDate>Sat, 02 May 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Linear's diagnosis is correct — issue tracking is over. But the fix isn't smarter tickets. It's the loop that should run before anything becomes a ticket at all.]]></description>
            <content:encoded><![CDATA[Linear's diagnosis is correct — issue tracking is over. But the fix isn't smarter tickets. It's the loop that should run before anything becomes a ticket at all.]]></content:encoded>
            <author>hello@pathmode.io (Janne Lammi)</author>
        </item>
        <item>
            <title><![CDATA[Knowledge Over Code: What Karpathy's Token Shift Means for Product Teams]]></title>
            <link>https://pathmode.io/blog/knowledge-over-code</link>
            <guid isPermaLink="false">https://pathmode.io/blog/knowledge-over-code</guid>
            <pubDate>Sat, 04 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Karpathy now routes more tokens into knowledge than code. This isn't a quirk — it's the industry bottleneck shifting upstream. What it means for teams building with AI agents.]]></description>
            <content:encoded><![CDATA[Karpathy now routes more tokens into knowledge than code. This isn't a quirk — it's the industry bottleneck shifting upstream. What it means for teams building with AI agents.]]></content:encoded>
            <author>hello@pathmode.io (Janne Lammi)</author>
        </item>
        <item>
            <title><![CDATA[The Next Product Discipline Isn't Context Engineering. It's Intent Engineering.]]></title>
            <link>https://pathmode.io/blog/intent-engineering-vs-context-engineering</link>
            <guid isPermaLink="false">https://pathmode.io/blog/intent-engineering-vs-context-engineering</guid>
            <pubDate>Wed, 25 Mar 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Context engineering became popular because AI exposed a communication problem. Intent engineering matters more because AI exposed a decision problem. Here's why product teams should focus on intent first.]]></description>
            <content:encoded><![CDATA[Context engineering became popular because AI exposed a communication problem. Intent engineering matters more because AI exposed a decision problem. Here's why product teams should focus on intent first.]]></content:encoded>
            <author>hello@pathmode.io (Janne Lammi)</author>
        </item>
        <item>
            <title><![CDATA[Anthropic's 2026 Agentic Coding Trends Report: Summary & Key Findings]]></title>
            <link>https://pathmode.io/blog/orchestration-era-needs-intent</link>
            <guid isPermaLink="false">https://pathmode.io/blog/orchestration-era-needs-intent</guid>
            <pubDate>Wed, 11 Mar 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[A summary of Anthropic's 2026 Agentic Coding Trends Report — the key findings, eight trends, and what the 60% usage vs 0–20% delegation gap means for product teams building with AI.]]></description>
            <content:encoded><![CDATA[A summary of Anthropic's 2026 Agentic Coding Trends Report — the key findings, eight trends, and what the 60% usage vs 0–20% delegation gap means for product teams building with AI.]]></content:encoded>
            <author>hello@pathmode.io (Janne Lammi)</author>
        </item>
        <item>
            <title><![CDATA[The Backlog Is Dead. Now What?]]></title>
            <link>https://pathmode.io/blog/the-backlog-is-dead-now-what</link>
            <guid isPermaLink="false">https://pathmode.io/blog/the-backlog-is-dead-now-what</guid>
            <pubDate>Fri, 06 Mar 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Issue tracking is dying because AI collapsed the cost of fixing. But the harder question — what to build and why — just got louder. The backlog's successor isn't nothing. It's structured intent.]]></description>
            <content:encoded><![CDATA[Issue tracking is dying because AI collapsed the cost of fixing. But the harder question — what to build and why — just got louder. The backlog's successor isn't nothing. It's structured intent.]]></content:encoded>
            <author>hello@pathmode.io (Janne Lammi)</author>
        </item>
        <item>
            <title><![CDATA[What Is Intent Engineering? The Discipline That Replaced Prompt Engineering]]></title>
            <link>https://pathmode.io/blog/what-is-intent-engineering</link>
            <guid isPermaLink="false">https://pathmode.io/blog/what-is-intent-engineering</guid>
            <pubDate>Wed, 04 Mar 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Intent engineering is how product teams specify what to build precisely enough for AI agents to execute without guessing. Here's the complete guide: what it is, why it matters, and how to practice it.]]></description>
            <content:encoded><![CDATA[Intent engineering is how product teams specify what to build precisely enough for AI agents to execute without guessing. Here's the complete guide: what it is, why it matters, and how to practice it.]]></content:encoded>
            <author>hello@pathmode.io (Janne Lammi)</author>
        </item>
        <item>
            <title><![CDATA[From Static Docs to Living Specs]]></title>
            <link>https://pathmode.io/blog/from-static-docs-to-living-specs</link>
            <guid isPermaLink="false">https://pathmode.io/blog/from-static-docs-to-living-specs</guid>
            <pubDate>Mon, 02 Mar 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[A spec that doesn't change after it's written is a spec that's already wrong. Here's how we made specs react to evidence, survive review, and grade their own implementation.]]></description>
            <content:encoded><![CDATA[A spec that doesn't change after it's written is a spec that's already wrong. Here's how we made specs react to evidence, survive review, and grade their own implementation.]]></content:encoded>
            <author>hello@pathmode.io (Janne Lammi)</author>
        </item>
        <item>
            <title><![CDATA[Prompting Split Into 4 Skills — Only One of Them Scales]]></title>
            <link>https://pathmode.io/blog/prompting-split-into-four-skills</link>
            <guid isPermaLink="false">https://pathmode.io/blog/prompting-split-into-four-skills</guid>
            <pubDate>Sun, 01 Mar 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[The industry is noticing that 'prompting' has fragmented into multiple disciplines. That's not a sign the skill is evolving. It's a sign it's the wrong abstraction.]]></description>
            <content:encoded><![CDATA[The industry is noticing that 'prompting' has fragmented into multiple disciplines. That's not a sign the skill is evolving. It's a sign it's the wrong abstraction.]]></content:encoded>
            <author>hello@pathmode.io (Janne Lammi)</author>
        </item>
        <item>
            <title><![CDATA[YC Is Right About the Problem. The Name Will Kill the Solution.]]></title>
            <link>https://pathmode.io/blog/yc-got-it-wrong</link>
            <guid isPermaLink="false">https://pathmode.io/blog/yc-got-it-wrong</guid>
            <pubDate>Wed, 25 Feb 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Y Combinator's Spring 2026 RFS nails the problem: teams need help figuring out what to build. But calling it 'Cursor for PMs' mis-categorizes a stack problem as a persona tool.]]></description>
            <content:encoded><![CDATA[Y Combinator's Spring 2026 RFS nails the problem: teams need help figuring out what to build. But calling it 'Cursor for PMs' mis-categorizes a stack problem as a persona tool.]]></content:encoded>
            <author>hello@pathmode.io (Janne Lammi)</author>
        </item>
        <item>
            <title><![CDATA[Why Your AI Prompts Fail: The Missing Layer Between Intent and Output]]></title>
            <link>https://pathmode.io/blog/why-your-ai-prompts-fail</link>
            <guid isPermaLink="false">https://pathmode.io/blog/why-your-ai-prompts-fail</guid>
            <pubDate>Fri, 13 Feb 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Your prompts aren't the problem. What's missing is everything that should exist before you write them.]]></description>
            <content:encoded><![CDATA[Your prompts aren't the problem. What's missing is everything that should exist before you write them.]]></content:encoded>
            <author>hello@pathmode.io (Janne Lammi)</author>
        </item>
        <item>
            <title><![CDATA[Direct Design Needs an Intent Layer]]></title>
            <link>https://pathmode.io/blog/direct-design-needs-intent</link>
            <guid isPermaLink="false">https://pathmode.io/blog/direct-design-needs-intent</guid>
            <pubDate>Thu, 12 Feb 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Direct Design removes the handoff between design and code. But someone still has to know what to build. That's the harder problem—and it was always upstream.]]></description>
            <content:encoded><![CDATA[Direct Design removes the handoff between design and code. But someone still has to know what to build. That's the harder problem—and it was always upstream.]]></content:encoded>
            <author>hello@pathmode.io (Janne Lammi)</author>
        </item>
        <item>
            <title><![CDATA[Why Jira Tickets Fail AI Agents]]></title>
            <link>https://pathmode.io/blog/why-jira-tickets-fail-ai-agents</link>
            <guid isPermaLink="false">https://pathmode.io/blog/why-jira-tickets-fail-ai-agents</guid>
            <pubDate>Wed, 04 Feb 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[You gave your AI agent access to Jira. It read every ticket. It still built the wrong thing. Here's why.]]></description>
            <content:encoded><![CDATA[You gave your AI agent access to Jira. It read every ticket. It still built the wrong thing. Here's why.]]></content:encoded>
            <author>hello@pathmode.io (Janne Lammi)</author>
        </item>
        <item>
            <title><![CDATA[The Sparse Bits Between]]></title>
            <link>https://pathmode.io/blog/the-sparse-bits-between</link>
            <guid isPermaLink="false">https://pathmode.io/blog/the-sparse-bits-between</guid>
            <pubDate>Sat, 31 Jan 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Andrej Karpathy says the programmer's contribution is now 'sparse and between.' That's not a problem—it's a signal. The bits that remain are the ones that matter most.]]></description>
            <content:encoded><![CDATA[Andrej Karpathy says the programmer's contribution is now 'sparse and between.' That's not a problem—it's a signal. The bits that remain are the ones that matter most.]]></content:encoded>
            <author>hello@pathmode.io (Pathmode Team)</author>
        </item>
        <item>
            <title><![CDATA[AI Agents Don't Close the Gap]]></title>
            <link>https://pathmode.io/blog/agents-dont-close-the-gap</link>
            <guid isPermaLink="false">https://pathmode.io/blog/agents-dont-close-the-gap</guid>
            <pubDate>Fri, 30 Jan 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Speed has never been the thing holding product teams back. The real bottleneck isn't code generation—it's definition.]]></description>
            <content:encoded><![CDATA[Speed has never been the thing holding product teams back. The real bottleneck isn't code generation—it's definition.]]></content:encoded>
            <author>hello@pathmode.io (Pathmode Team)</author>
        </item>
        <item>
            <title><![CDATA[The Double Diamond is Cracking]]></title>
            <link>https://pathmode.io/blog/the-double-diamond-is-cracking</link>
            <guid isPermaLink="false">https://pathmode.io/blog/the-double-diamond-is-cracking</guid>
            <pubDate>Sun, 25 Jan 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[The Double Diamond assumes execution is expensive. AI just made it instant. The framework isn't wrong—it's built for a world that no longer exists.]]></description>
            <content:encoded><![CDATA[The Double Diamond assumes execution is expensive. AI just made it instant. The framework isn't wrong—it's built for a world that no longer exists.]]></content:encoded>
            <author>hello@pathmode.io (Janne Lammi)</author>
        </item>
        <item>
            <title><![CDATA[AI-Native Teams Need an Intent Layer]]></title>
            <link>https://pathmode.io/blog/ai-native-teams-need-intent</link>
            <guid isPermaLink="false">https://pathmode.io/blog/ai-native-teams-need-intent</guid>
            <pubDate>Tue, 20 Jan 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Brian Balfour describes the 'what' of AI-native product teams. Here's the 'how.']]></description>
            <content:encoded><![CDATA[Brian Balfour describes the 'what' of AI-native product teams. Here's the 'how.']]></content:encoded>
            <author>hello@pathmode.io (Janne Lammi)</author>
        </item>
        <item>
            <title><![CDATA[The Vibe Coding Hangover]]></title>
            <link>https://pathmode.io/blog/the-vibe-coding-hangover</link>
            <guid isPermaLink="false">https://pathmode.io/blog/the-vibe-coding-hangover</guid>
            <pubDate>Sun, 18 Jan 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Vibe coding feels like a superpower—until the second developer joins. Here's what happens when AI-generated codebases meet real teams, and why intent is the cure.]]></description>
            <content:encoded><![CDATA[Vibe coding feels like a superpower—until the second developer joins. Here's what happens when AI-generated codebases meet real teams, and why intent is the cure.]]></content:encoded>
            <author>hello@pathmode.io (Janne Lammi)</author>
        </item>
        <item>
            <title><![CDATA[The Intent Layer]]></title>
            <link>https://pathmode.io/blog/intent-layer</link>
            <guid isPermaLink="false">https://pathmode.io/blog/intent-layer</guid>
            <pubDate>Fri, 16 Jan 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Agentic AI doesn't need prompts. It needs intent—structured, contextual, traceable to user friction. Here's the full framework for the missing layer in the software stack.]]></description>
            <content:encoded><![CDATA[Agentic AI doesn't need prompts. It needs intent—structured, contextual, traceable to user friction. Here's the full framework for the missing layer in the software stack.]]></content:encoded>
            <author>hello@pathmode.io (Janne Lammi)</author>
        </item>
        <item>
            <title><![CDATA[Design is More Than Code—But Where Do You Design the Problem?]]></title>
            <link>https://pathmode.io/blog/design-is-more-than-code</link>
            <guid isPermaLink="false">https://pathmode.io/blog/design-is-more-than-code</guid>
            <pubDate>Wed, 14 Jan 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Karri Saarinen is right: we are over-indexing on execution. But the answer isn't just 'more consideration.' It's building infrastructure that makes problem definition a first-class artifact.]]></description>
            <content:encoded><![CDATA[Karri Saarinen is right: we are over-indexing on execution. But the answer isn't just 'more consideration.' It's building infrastructure that makes problem definition a first-class artifact.]]></content:encoded>
            <author>hello@pathmode.io (Janne Lammi)</author>
        </item>
        <item>
            <title><![CDATA[Your Title is a Lens, Not a Lane]]></title>
            <link>https://pathmode.io/blog/title-is-a-lens</link>
            <guid isPermaLink="false">https://pathmode.io/blog/title-is-a-lens</guid>
            <pubDate>Mon, 12 Jan 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Designers don't just make Figma files. PMs don't just write specs. As AI collapses the implementation layer, what remains is judgment—and the ability to ship.]]></description>
            <content:encoded><![CDATA[Designers don't just make Figma files. PMs don't just write specs. As AI collapses the implementation layer, what remains is judgment—and the ability to ship.]]></content:encoded>
            <author>hello@pathmode.io (Janne Lammi)</author>
        </item>
        <item>
            <title><![CDATA[The Spec is Becoming the Product]]></title>
            <link>https://pathmode.io/blog/spec-is-the-product</link>
            <guid isPermaLink="false">https://pathmode.io/blog/spec-is-the-product</guid>
            <pubDate>Thu, 08 Jan 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[When agents execute directly from specs, the spec is no longer a handoff document. It's the highest-leverage artifact your team produces.]]></description>
            <content:encoded><![CDATA[When agents execute directly from specs, the spec is no longer a handoff document. It's the highest-leverage artifact your team produces.]]></content:encoded>
            <author>hello@pathmode.io (Janne Lammi)</author>
        </item>
        <item>
            <title><![CDATA[The Disappearing Middle of Software Work]]></title>
            <link>https://pathmode.io/blog/disappearing-middle</link>
            <guid isPermaLink="false">https://pathmode.io/blog/disappearing-middle</guid>
            <pubDate>Wed, 07 Jan 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[As AI agents handle implementation, the craft of software shifts to the ends: defining intent and verifying outcomes. The teams that master both will build the best products.]]></description>
            <content:encoded><![CDATA[As AI agents handle implementation, the craft of software shifts to the ends: defining intent and verifying outcomes. The teams that master both will build the best products.]]></content:encoded>
            <author>hello@pathmode.io (Janne Lammi)</author>
        </item>
        <item>
            <title><![CDATA[The Case Against Research Repositories]]></title>
            <link>https://pathmode.io/blog/execution-over-management</link>
            <guid isPermaLink="false">https://pathmode.io/blog/execution-over-management</guid>
            <pubDate>Sat, 03 Jan 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Research repositories were built to store insights. But storage is not the goal; shipping is. To build better products, we must move from passive libraries to active design engines.]]></description>
            <content:encoded><![CDATA[Research repositories were built to store insights. But storage is not the goal; shipping is. To build better products, we must move from passive libraries to active design engines.]]></content:encoded>
            <author>hello@pathmode.io (Janne Lammi)</author>
        </item>
    </channel>
</rss>