<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Chris Lema</title><description>Thoughts on product management, WordPress, WooCommerce, leadership, and coaching from Chris Lema.</description><link>https://chrislema.com/</link><item><title>Your Voice Won&apos;t Die From Using AI. It&apos;ll Die From Agreeing With It.</title><link>https://chrislema.com/your-voice-wont-die-from-using-ai/</link><guid isPermaLink="true">https://chrislema.com/your-voice-wont-die-from-using-ai/</guid><description>The real threat AI poses to your voice isn&apos;t reduced typing, it&apos;s the erosion of your taste every time you approve a suggestion instead of overruling it. Keep your voice upstream (the deciding) and confine AI downstream (the executing) by making four non-delegable calls before you generate a word.</description><pubDate>Thu, 25 Jun 2026 12:00:00 GMT</pubDate><category>AI</category><category>For Creators</category><category>AI Content</category></item><item><title>You&apos;ve installed a Claude Skill and it&apos;s not working. How to fix it.</title><link>https://chrislema.com/youve-installed-a-claude-skill-and-its-not-working-how-to-fix-it/</link><guid isPermaLink="true">https://chrislema.com/youve-installed-a-claude-skill-and-its-not-working-how-to-fix-it/</guid><description>You installed a Claude skill someone else published and it just sits there, never running. That isn&apos;t a broken skill, it&apos;s how skills load. Here&apos;s why it happens, how to tell, and two ways to fix it, including one that needs no editing at all.</description><pubDate>Tue, 23 Jun 2026 12:00:00 GMT</pubDate><category>AI</category><category>For Creators</category><category>Claude Skills</category></item><item><title>The Video You&apos;ve Been Putting Off Takes Five Minutes Now</title><link>https://chrislema.com/the-video-youve-been-putting-off-takes-five-minutes-now/</link><guid isPermaLink="true">https://chrislema.com/the-video-youve-been-putting-off-takes-five-minutes-now/</guid><description>You shipped something real and nobody knows it exists. Video used to mean gear, a crew, and an edit. Now it&apos;s a short script and about five minutes, which moves the hard part to whether you&apos;ve got something worth watching.</description><pubDate>Sun, 21 Jun 2026 12:00:00 GMT</pubDate><category>AI</category><category>For Founders</category><category>AI Adoption</category><category>AI Content</category><enclosure url="https://media.chrislema.com/talking-head-video.png" length="2333118" type="image/png"/></item><item><title>Encoded Judgment: How a Cheap Model Performs Like an Expensive One</title><link>https://chrislema.com/encoded-judgment-cheap-model-performs-like-expensive/</link><guid isPermaLink="true">https://chrislema.com/encoded-judgment-cheap-model-performs-like-expensive/</guid><description>I ran a product team that captured every customer question into a playbook before handing it off. That old loop is exactly how you make a cheap AI model carry expensive work.</description><pubDate>Thu, 18 Jun 2026 12:00:00 GMT</pubDate><category>AI</category><category>Encoding Expertise</category><category>AI Economics</category><category>For Engineers</category><enclosure url="https://media.chrislema.com/benchmark.png" length="630521" type="image/png"/></item><item><title>Loop Engineering: For me it&apos;s about using dumber models and smarter code</title><link>https://chrislema.com/loop-engineering-dumber-models-smarter-code/</link><guid isPermaLink="true">https://chrislema.com/loop-engineering-dumber-models-smarter-code/</guid><description>My take on loop engineering: push judgment onto dumber, cheaper models and smarter code over time, so a long-running agent gets cheaper and more trustworthy with use.</description><pubDate>Tue, 16 Jun 2026 12:00:00 GMT</pubDate><category>AI</category><category>Agentic Software</category><category>Encoding Expertise</category><category>AI Economics</category><category>For Engineers</category><enclosure url="https://media.chrislema.com/loop-engineering.png" length="152185" type="image/png"/></item><item><title>What AI Found Hiding in 74 Posts I Never Planned</title><link>https://chrislema.com/using-ai-to-organize-my-blog/</link><guid isPermaLink="true">https://chrislema.com/using-ai-to-organize-my-blog/</guid><description>I put AI to work on the boring part of my site: reading 74 posts to surface the topics, audiences, and cross-links that were hiding in them all along.</description><pubDate>Sun, 14 Jun 2026 12:00:00 GMT</pubDate><category>AI</category><category>AI Content</category><category>AI Adoption</category><category>For Creators</category></item><item><title>Inside a Claude Skill: The Eight Steps That Build the Red Dot skill</title><link>https://chrislema.com/inside-the-claude-skill-that-builds-assessments/</link><guid isPermaLink="true">https://chrislema.com/inside-the-claude-skill-that-builds-assessments/</guid><description>I open the hood on the Claude Skill that builds mirror assessments — the eight-step pipeline, the single spec it compiles, and the checker that won&apos;t ship broken.</description><pubDate>Tue, 09 Jun 2026 12:00:00 GMT</pubDate><category>AI</category><category>Product Work</category><category>Claude Skills</category><category>Evals</category><category>For Engineers</category></item><item><title>How a Claude Skill Converts Leads With a Quiz</title><link>https://chrislema.com/claude-skill-converts-leads-with-a-quiz/</link><guid isPermaLink="true">https://chrislema.com/claude-skill-converts-leads-with-a-quiz/</guid><description>I gave a one-page brief to a new Claude Skill and got back a working lead-gen quiz — a design doc and a hostable assessment. Here&apos;s how the skill does it.</description><pubDate>Sun, 07 Jun 2026 12:00:00 GMT</pubDate><category>AI</category><category>Product Work</category><category>Claude Skills</category><category>Encoding Expertise</category><category>For Consultants</category></item><item><title>Everyone needs a Custom Assessment</title><link>https://chrislema.com/custom-assessment/</link><guid isPermaLink="true">https://chrislema.com/custom-assessment/</guid><description>Everyone needs a custom assessment, and when you think of your own experiences, you&apos;ll agree with me.</description><pubDate>Thu, 04 Jun 2026 12:00:00 GMT</pubDate><category>AI</category><category>Product Work</category><category>Encoding Expertise</category><category>For Consultants</category></item><item><title>Five Paradigm Shifts You Need to Embrace About AI</title><link>https://chrislema.com/five-paradigm-shifts-to-embrace-about-ai/</link><guid isPermaLink="true">https://chrislema.com/five-paradigm-shifts-to-embrace-about-ai/</guid><description>Five paradigm shifts from three years building with AI: design time over runtime, judgment over prompts, real feedback loops, conversation, and knowledge that&apos;s built, not stored.</description><pubDate>Mon, 01 Jun 2026 13:00:00 GMT</pubDate><category>AI</category><category>Product Work</category><category>Encoding Expertise</category><category>AI Economics</category><category>For Founders</category><enclosure url="https://media.chrislema.com/five-paradigms-ai.png" length="156671" type="image/png"/></item><item><title>How to Tell If Your Scoreboard Is Lying to You</title><link>https://chrislema.com/scoreboard-lying-to-you/</link><guid isPermaLink="true">https://chrislema.com/scoreboard-lying-to-you/</guid><description>A pizza shop&apos;s flyer contest shows why your AI scoreboard can climb while the work gets worse - and why a measure that can&apos;t be gamed is the real job.</description><pubDate>Sat, 30 May 2026 13:00:00 GMT</pubDate><category>AI</category><category>Product Work</category><category>Evals</category><category>For Engineers</category><enclosure url="https://media.chrislema.com/scoreboard-is-lying.png" length="149778" type="image/png"/></item><item><title>Knowledge Isn&apos;t Stored. It&apos;s Built.</title><link>https://chrislema.com/knowledge-isnt-stored-its-built/</link><guid isPermaLink="true">https://chrislema.com/knowledge-isnt-stored-its-built/</guid><description>Why storage is the wrong question for knowledge, and how decomposing content into a graph builds answers no document ever held. The MCode Coach story.</description><pubDate>Thu, 28 May 2026 13:00:00 GMT</pubDate><category>AI</category><category>Encoding Expertise</category><category>For Consultants</category><enclosure url="https://media.chrislema.com/MCode-Knowledge-Graph.png" length="3180737" type="image/png"/></item><item><title>Ten Conversations to have with Claude before Vibe Coding</title><link>https://chrislema.com/ten-conversations-before-vibe-coding/</link><guid isPermaLink="true">https://chrislema.com/ten-conversations-before-vibe-coding/</guid><description>One prompt gets you something. Ten conversations get you something better. Here are the ten you should have with Claude before any code gets written.</description><pubDate>Tue, 26 May 2026 13:00:00 GMT</pubDate><category>AI</category><category>Product Work</category><category>Vibe Coding</category><category>For Founders</category><enclosure url="https://media.chrislema.com/10-conversations.png" length="137357" type="image/png"/></item><item><title>How to Stop Burning AI Budget Without Stopping What AI Lets You Do</title><link>https://chrislema.com/stop-burning-ai-budget/</link><guid isPermaLink="true">https://chrislema.com/stop-burning-ai-budget/</guid><description>Companies are blowing through AI budgets, but pricing isn&apos;t the real cause. Two habits keep my bills flat without rolling back what AI lets me do.</description><pubDate>Sun, 24 May 2026 13:00:00 GMT</pubDate><category>AI</category><category>AI Economics</category><category>For Executives</category></item><item><title>The Key Comes Before the Song</title><link>https://chrislema.com/the-key-comes-before-the-song/</link><guid isPermaLink="true">https://chrislema.com/the-key-comes-before-the-song/</guid><description>When you build with AI doing the content generation, the obvious move is QA at the end. But if that&apos;s your whole strategy, you sat down at the piano without picking a key. Here&apos;s how I&apos;m thinking about evals for a new product — and why guardrails belong upstream, not downstream.</description><pubDate>Fri, 22 May 2026 13:00:00 GMT</pubDate><category>AI</category><category>Product Work</category><category>Evals</category><category>For Engineers</category></item><item><title>Use Claude to get you questions, not answers</title><link>https://chrislema.com/claude-session-more-questions-not-answers/</link><guid isPermaLink="true">https://chrislema.com/claude-session-more-questions-not-answers/</guid><description>Most Claude sessions produce transcripts because users ask for answers. The posture that produces real specifications looks different. Here&apos;s what it requires.</description><pubDate>Wed, 20 May 2026 13:00:00 GMT</pubDate><category>AI</category><category>AI Adoption</category><category>For Founders</category><enclosure url="https://media.chrislema.com/questions-not-answers.png" length="166724" type="image/png"/></item><item><title>Stop Selling a Privacy Policy</title><link>https://chrislema.com/stop-selling-privacy-policy-ship-privacy-protocol/</link><guid isPermaLink="true">https://chrislema.com/stop-selling-privacy-policy-ship-privacy-protocol/</guid><description>When both sides have IP, current AI privacy answers force one of them to bleed. The fix isn&apos;t a better policy or a clever cryptographic trick. It&apos;s a design discipline: stop protecting what crosses the wire and start designing what&apos;s allowed to cross in the first place.</description><pubDate>Mon, 18 May 2026 13:00:00 GMT</pubDate><category>AI</category><category>Product Work</category><category>For Engineers</category><category>For Founders</category><enclosure url="https://media.chrislema.com/stop-selling-a-privacy-policy.png" length="156324" type="image/png"/></item><item><title>You don&apos;t have to be technical to own the architecture</title><link>https://chrislema.com/own-the-architecture/</link><guid isPermaLink="true">https://chrislema.com/own-the-architecture/</guid><description>AI is changing everything and nothing at the same time. So where should you spend your scarce time? Three things will always matter: your domain, systems thinking, and architecture. And architecture isn&apos;t what most people think it is. It&apos;s the load-bearing decisions you care about, written down before the AI builds the wrong thing.</description><pubDate>Sat, 16 May 2026 17:00:00 GMT</pubDate><category>AI</category><category>Product Work</category><category>Vibe Coding</category><category>For Founders</category><enclosure url="https://media.chrislema.com/i-got-it-1.png" length="1028249" type="image/png"/></item><item><title>The 4 scans I run before I&apos;m done with any AI-assisted project</title><link>https://chrislema.com/four-scans-ai-assisted-projects/</link><guid isPermaLink="true">https://chrislema.com/four-scans-ai-assisted-projects/</guid><description>There are no magic prompts. But there are four scans I run after every first pass on AI-assisted code: race conditions, concurrency, idempotency, and dead code. Each one catches issues you&apos;d otherwise debug months later.</description><pubDate>Thu, 14 May 2026 13:00:00 GMT</pubDate><category>AI</category><category>Product Work</category><category>Evals</category><category>For Engineers</category><enclosure url="https://media.chrislema.com/4-scans.png" length="180387" type="image/png"/></item><item><title>Lovable, and the cardboard model problem</title><link>https://chrislema.com/lovable-cardboard-model-problem/</link><guid isPermaLink="true">https://chrislema.com/lovable-cardboard-model-problem/</guid><description>Most people who have ideas aren&apos;t developers, so their ideas live and die in one head. Lovable changes the cost of building a cardboard model to roughly zero. Here&apos;s what that means for the conversations you can finally have.</description><pubDate>Tue, 12 May 2026 12:00:00 GMT</pubDate><category>AI</category><category>Product Work</category><category>Vibe Coding</category><category>For Founders</category><enclosure url="https://media.chrislema.com/lovable-cardboard-model.png" length="144658" type="image/png"/></item><item><title>The harness is the craft.</title><link>https://chrislema.com/the-harness-is-the-craft/</link><guid isPermaLink="true">https://chrislema.com/the-harness-is-the-craft/</guid><description>Most engineers pick a model they trust, eyeball a couple of runs, and ship. I don&apos;t ship that way. Here&apos;s what eval-driven development actually looks like, and the seven principles I&apos;d hand to anyone shipping LLM systems.</description><pubDate>Sun, 10 May 2026 12:00:00 GMT</pubDate><category>AI</category><category>Product Work</category><category>Evals</category><category>For Engineers</category><enclosure url="https://media.chrislema.com/the-harness-is-the-craft.png" length="153840" type="image/png"/></item><item><title>What Is a Claude Skill? Let&apos;s Look Closely at One.</title><link>https://chrislema.com/what-is-a-claude-skill/</link><guid isPermaLink="true">https://chrislema.com/what-is-a-claude-skill/</guid><description>A Claude Skill teaches AI to work the way you want, not the average way. Here&apos;s a walkthrough of one I built (Expert Profiler) and the install pattern you can reuse for any technical setup.</description><pubDate>Fri, 08 May 2026 12:00:00 GMT</pubDate><category>AI</category><category>Claude Skills</category><category>For Engineers</category><category>For Founders</category><enclosure url="https://media.chrislema.com/what-is-a--claude-skill.png" length="178638" type="image/png"/></item><item><title>Why Your AI Bill Is Too High (And the Architecture Fix That Saves 40%)</title><link>https://chrislema.com/ai-bill-too-high-architecture-fix-saves-40-percent/</link><guid isPermaLink="true">https://chrislema.com/ai-bill-too-high-architecture-fix-saves-40-percent/</guid><description>Most companies run their AI like a doctor&apos;s office. The ones that scale run it like an ER. Here&apos;s the architecture decision that cuts AI costs by 40%.</description><pubDate>Wed, 06 May 2026 12:00:00 GMT</pubDate><category>AI</category><category>Product Work</category><category>AI Economics</category><category>Agentic Software</category><category>For Engineers</category><category>For Executives</category><enclosure url="https://media.chrislema.com/ai-bill-too-high.png" length="174206" type="image/png"/></item><item><title>The CRM I built this weekend doesn&apos;t have a UI. Agentic Software is the future.</title><link>https://chrislema.com/agentic-software-crm-no-ui/</link><guid isPermaLink="true">https://chrislema.com/agentic-software-crm-no-ui/</guid><description>I built a CRM this weekend with no UI. Just tools an AI agent can call. Here&apos;s why agentic software is the next decade of building.</description><pubDate>Mon, 04 May 2026 12:00:00 GMT</pubDate><category>AI</category><category>Product Work</category><category>Agentic Software</category><category>For Engineers</category><enclosure url="https://media.chrislema.com/Headlesscrm1.png" length="420420" type="image/png"/></item><item><title>You Vibe-Coded Something That Works. Here&apos;s How to Make It Real Without Touching the Code Yourself.</title><link>https://chrislema.com/vibe-coded-something-that-works-now-what/</link><guid isPermaLink="true">https://chrislema.com/vibe-coded-something-that-works-now-what/</guid><description>Vibe coding tools get you to a working draft in an afternoon. The next pass has a name and a shape. Five layers your AI can add for you.</description><pubDate>Sat, 02 May 2026 12:00:00 GMT</pubDate><category>AI</category><category>Product Work</category><category>Vibe Coding</category><category>Encoding Expertise</category><category>For Founders</category><enclosure url="https://media.chrislema.com/vibe-coding-app.png" length="785738" type="image/png"/></item></channel></rss>