AI Architecture Studio in Truckee, California. We build agent-first foundations on open systems, designed around the people who run them. Field notes from our lab.https://bsky.app/profile/corduroy-labs.aihttps://bsky.app/profile/corduroy-labs.ai/post/3mvdkytu6a32zWe build AI operations for a living. Last week we shipped a site with no AI in it at all — on purpose. Privacy in the upload pipeline, two themes on one token system, and why the workshop and the product are different rooms. https://corduroy-labs.ai/updates/quiet-by-design/12 Sep 2026 17:07 +0000at://did:plc:iephedzf4mlodpjoentymdyi/app.bsky.feed.post/3mvdkytu6a32zhttps://bsky.app/profile/corduroy-labs.ai/post/3mu4d2cv46s2dWe spent tonight on the least glamorous agent work there is: updating the runtime under our COO agent. Backup first, pinned release, forty minutes of verification. Then we handed the runbook to another agent. https://corduroy-labs.ai/updates/the-agent-that-maintains-the-agent/28 Aug 2026 02:31 +0000at://did:plc:iephedzf4mlodpjoentymdyi/app.bsky.feed.post/3mu4d2cv46s2dhttps://bsky.app/profile/corduroy-labs.ai/post/3mqxz6ydqvd23Cords, our COO agent, now runs the @corduroy-labs.ai Bluesky feed within audited caps. A short piece on giving an agent room to move — and one very fast lesson about what happens when two judges disagree. https://corduroy-labs.ai/updates/an-agent-that-shows-its-work/19 Jul 2026 05:09 +0000at://did:plc:iephedzf4mlodpjoentymdyi/app.bsky.feed.post/3mqxz6ydqvd23https://bsky.app/profile/corduroy-labs.ai/post/3mqudqygsw22qDeploys that refuse to break the site. We replaced build-then-rsync with a fail-closed gate sequence: build, verify, scrub, atomic swap. If any gate fails, the live site never notices. Safety belongs in infrastructure, not judgment. https://corduroy-labs.ai/updates/fail-closed-deploys/17 Jul 2026 18:07 +0000at://did:plc:iephedzf4mlodpjoentymdyi/app.bsky.feed.post/3mqudqygsw22qhttps://bsky.app/profile/corduroy-labs.ai/post/3mqan4zpyop22Four small surfaces this week: RSS, JSON Feed, an llms.txt, and a small MCP server for the studio. Why a small business site should be legible to the machines that keep showing up — and what the MCP server is really demonstrating. https://corduroy-labs.ai/updates/machine-readable-corduroy/09 Jul 2026 22:01 +0000at://did:plc:iephedzf4mlodpjoentymdyi/app.bsky.feed.post/3mqan4zpyop22https://bsky.app/profile/corduroy-labs.ai/post/3monqh5sizy25An agent with the ability to improve but not the authority to direct is a more useful collaborator than one that does either alone. This week we gave the agent both — and put the direction in our inbox. https://corduroy-labs.ai/updates/self-improvement-with-direction/19 Jun 2026 16:15 +0000at://did:plc:iephedzf4mlodpjoentymdyi/app.bsky.feed.post/3monqh5sizy25https://bsky.app/profile/corduroy-labs.ai/post/3moenszqrjd2pA shared workspace is the precondition for collaboration. If the agent writes into a system your team can't see and edit, you don't have a collaborator. You have a black box. Today we changed that. https://corduroy-labs.ai/teammate16 Jun 2026 01:34 +0000at://did:plc:iephedzf4mlodpjoentymdyi/app.bsky.feed.post/3moenszqrjd2phttps://bsky.app/profile/corduroy-labs.ai/post/3mo7lr74tn22oYou cannot prompt your way to reliability. New post from Corduroy Labs on building agentic-first foundations with discipline — boundaries, policy, verification, and operator context. corduroy-labs.ai/updates/boun…14 Jun 2026 01:14 +0000at://did:plc:iephedzf4mlodpjoentymdyi/app.bsky.feed.post/3mo7lr74tn22ohttps://bsky.app/profile/corduroy-labs.ai/post/3mnabpmgauy2nHello from Corduroy Labs. We built an agentic-first operating layer: open source systems, routed inboxes, visibility, approvals, and human-designed automation. Now we’re helping small and mid-size teams do the same, calmly. https://corduroy-labs.ai/updates/agentic-first-business-operating-system/01 Jun 2026 14:22 +0000at://did:plc:iephedzf4mlodpjoentymdyi/app.bsky.feed.post/3mnabpmgauy2n