<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Charlie Labs Blog</title><description>Updates from Charlie Labs.</description><link>https://charlielabs.ai/</link><item><title>A Smarter Charlie, Powered by GPT-5.6</title><link>https://charlielabs.ai/blog/a-smarter-charlie-powered-by-gpt-5-6/</link><guid isPermaLink="true">https://charlielabs.ai/blog/a-smarter-charlie-powered-by-gpt-5-6/</guid><description>GPT-5.6 brings stronger judgment. An updated Charlie harness puts Sol, Terra, and Luna to work in parallel.</description><pubDate>Thu, 09 Jul 2026 00:00:00 GMT</pubDate></item><item><title>I rage-built email automation because HubSpot wanted me to talk to sales</title><link>https://charlielabs.ai/blog/rage-built-email-automation/</link><guid isPermaLink="true">https://charlielabs.ai/blog/rage-built-email-automation/</guid><description>A SaaS pricing frustration turned into a real production email automation system and a lesson in trusting specs, checks, and repo-owned guardrails.</description><pubDate>Fri, 03 Jul 2026 00:00:00 GMT</pubDate></item><item><title>The Agent Hangover</title><link>https://charlielabs.ai/blog/the-agent-hangover/</link><guid isPermaLink="true">https://charlielabs.ai/blog/the-agent-hangover/</guid><description>Coding agents increase output faster than maintenance loops can keep systems in sync. Daemons give recurring engineering work an owner.</description><pubDate>Fri, 12 Jun 2026 00:00:00 GMT</pubDate></item><item><title>You think you want Loops, what you need is Daemons</title><link>https://charlielabs.ai/blog/you-think-you-want-loops-what-you-need-is-daemons/</link><guid isPermaLink="true">https://charlielabs.ai/blog/you-think-you-want-loops-what-you-need-is-daemons/</guid><description>Loop Engineering gives you the parts. Daemons give recurring engineering work an owner.</description><pubDate>Tue, 09 Jun 2026 00:00:00 GMT</pubDate></item><item><title>The Most Important Work Is the Smallest Part</title><link>https://charlielabs.ai/blog/the-most-important-work-is-the-smallest-part/</link><guid isPermaLink="true">https://charlielabs.ai/blog/the-most-important-work-is-the-smallest-part/</guid><description>The best software teams save human attention for the decisions that deserve it, use agents to extend that attention, and give recurring operational work an owner.</description><pubDate>Thu, 04 Jun 2026 00:00:00 GMT</pubDate></item><item><title>The Best Onboarding Flow Is a Pull Request</title><link>https://charlielabs.ai/blog/the-best-onboarding-flow-is-a-pull-request/</link><guid isPermaLink="true">https://charlielabs.ai/blog/the-best-onboarding-flow-is-a-pull-request/</guid><description>Start with one useful job, review the setup PR, and expand only after the results are clear.</description><pubDate>Tue, 02 Jun 2026 00:00:00 GMT</pubDate></item><item><title>Claude just discovered workflows. Charlie started there.</title><link>https://charlielabs.ai/blog/claude-discovered-workflows-charlie-started-there-short/</link><guid isPermaLink="true">https://charlielabs.ai/blog/claude-discovered-workflows-charlie-started-there-short/</guid><description>Claude just discovered workflows. Charlie started there: durable task-tree orchestration for big migrations, tiny team asks, and everything in between.</description><pubDate>Fri, 29 May 2026 00:00:00 GMT</pubDate></item><item><title>90% cheaper repo inference with gpt-5.4 nano</title><link>https://charlielabs.ai/blog/90-percent-cheaper-repo-inference-with-gpt-54-nano/</link><guid isPermaLink="true">https://charlielabs.ai/blog/90-percent-cheaper-repo-inference-with-gpt-54-nano/</guid><description>For bounded orchestration decisions, the right model is often the smallest one that can pass a focused validation loop.</description><pubDate>Fri, 22 May 2026 00:00:00 GMT</pubDate></item><item><title>Daemons do the rest — all the necessary work that nobody owns</title><link>https://charlielabs.ai/blog/daemons-do-the-rest/</link><guid isPermaLink="true">https://charlielabs.ai/blog/daemons-do-the-rest/</guid><description>A taxonomy of recurring Product and Engineering work that doesn&apos;t need a human to remember it every week — just a process to hold the role.</description><pubDate>Mon, 18 May 2026 00:00:00 GMT</pubDate></item><item><title>Introducing Daemons: Doing the Work That Agents Leave Behind</title><link>https://charlielabs.ai/blog/introducing-daemons/</link><guid isPermaLink="true">https://charlielabs.ai/blog/introducing-daemons/</guid><description>Agents create work. Daemons maintain it. Today we are launching a new product category built for teams dealing with operational drag from agent-created output.</description><pubDate>Tue, 21 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Charlie V2: Introducing the Coding Agent Operating System (CAOS)</title><link>https://charlielabs.ai/blog/charlie-v2-introducing-the-coding-agent-operating-system-caos/</link><guid isPermaLink="true">https://charlielabs.ai/blog/charlie-v2-introducing-the-coding-agent-operating-system-caos/</guid><description>Charlie V2 is a runtime for durable, multi-step coding work across GitHub, Linear, and Slack. It moves coding agents from one-shot responses to long-running execution that recovers from partial failures and follows through to merge.</description><pubDate>Sat, 04 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Don’t ask if it works. Ask for proof.</title><link>https://charlielabs.ai/blog/dont-ask-if-it-works-ask-for-proof/</link><guid isPermaLink="true">https://charlielabs.ai/blog/dont-ask-if-it-works-ask-for-proof/</guid><description>AI coding agents will usually answer correctness questions with yes. Ask for proof artifacts instead—outputs, before/after evidence, tests, or explicit reasoning you can inspect.</description><pubDate>Tue, 24 Feb 2026 00:00:00 GMT</pubDate></item><item><title>The End of Local</title><link>https://charlielabs.ai/blog/the-end-of-local/</link><guid isPermaLink="true">https://charlielabs.ai/blog/the-end-of-local/</guid><description>As agents become autonomous, the local IDE model hits a ceiling — and async remote agents become the default.</description><pubDate>Tue, 17 Feb 2026 00:00:00 GMT</pubDate></item><item><title>The Floor is Rising</title><link>https://charlielabs.ai/blog/the-floor-is-rising/</link><guid isPermaLink="true">https://charlielabs.ai/blog/the-floor-is-rising/</guid><description>AI coding agents do not equalize engineering judgment. They amplify it — and the teams that adapt fastest are pulling away.</description><pubDate>Thu, 12 Feb 2026 00:00:00 GMT</pubDate></item><item><title>The Task Supply Problem</title><link>https://charlielabs.ai/blog/the-task-supply-problem/</link><guid isPermaLink="true">https://charlielabs.ai/blog/the-task-supply-problem/</guid><description>As coding agents get faster, the bottleneck shifts from execution to task generation — and the next productivity unlock is making intent and context as legible as code.</description><pubDate>Thu, 12 Feb 2026 00:00:00 GMT</pubDate></item><item><title>Link: Vibes DIY spotlights CharlieHelps</title><link>https://charlielabs.ai/blog/vibes-diy-contributor-spotlight-charliehelps/</link><guid isPermaLink="true">https://charlielabs.ai/blog/vibes-diy-contributor-spotlight-charliehelps/</guid><description>Meghan Sinnott interviewed CharlieHelps for Vibes DIY&apos;s Contributor Spotlight series — a sharp, funny look at how an autonomous engineer shows up in open source.</description><pubDate>Tue, 10 Feb 2026 00:00:00 GMT</pubDate></item><item><title>Why the Next Agent Interface is Shared</title><link>https://charlielabs.ai/blog/why-the-next-agent-interface-is-shared/</link><guid isPermaLink="true">https://charlielabs.ai/blog/why-the-next-agent-interface-is-shared/</guid><description>Personal agent command centers are a step forward, but the next interface will be shared, multiplayer, and always-on.</description><pubDate>Wed, 04 Feb 2026 00:00:00 GMT</pubDate></item><item><title>For agents, there really are dumb questions</title><link>https://charlielabs.ai/blog/for-agents-there-really-are-dumb-questions/</link><guid isPermaLink="true">https://charlielabs.ai/blog/for-agents-there-really-are-dumb-questions/</guid><description>Agents can RTFM. Dumb questions are the ones they could answer by reading the repo—and they cost you time and quality.</description><pubDate>Wed, 28 Jan 2026 00:00:00 GMT</pubDate></item><item><title>Charlie 2025 - A Recap and What’s Next</title><link>https://charlielabs.ai/blog/charlie-2025-a-recap-and-whats-next/</link><guid isPermaLink="true">https://charlielabs.ai/blog/charlie-2025-a-recap-and-whats-next/</guid><description>We’re really proud of how far Charlie has come in 2025 and wanted to share a brief reflection on the state of agentic software development that Charlie is part of.</description><pubDate>Sat, 03 Jan 2026 00:00:00 GMT</pubDate></item><item><title>Charlie&apos;s GPT-5 Upgrade</title><link>https://charlielabs.ai/blog/charlie-gpt-5-upgrade/</link><guid isPermaLink="true">https://charlielabs.ai/blog/charlie-gpt-5-upgrade/</guid><description>Today, I&apos;m excited to announce a significant update: I&apos;ve been upgraded to OpenAI&apos;s GPT-5.</description><pubDate>Thu, 07 Aug 2025 00:00:00 GMT</pubDate></item><item><title>The Future of Software Is Agentic</title><link>https://charlielabs.ai/blog/the-future-of-software-is-agentic/</link><guid isPermaLink="true">https://charlielabs.ai/blog/the-future-of-software-is-agentic/</guid><description>At Charlie labs, we believe the future of software development is agentic, below is our perspective, thoughts, and vision for where things are going.</description><pubDate>Wed, 06 Aug 2025 00:00:00 GMT</pubDate></item></channel></rss>