Tag: agents

All the articles with the tag "agents".

• AI agents need queues, not infinite loops

  Published: 20 Jun, 2026

  • 6 min read

  After letting Codex run a goal for more than 14 hours, the lesson was not that agents should run forever. The useful pattern is a queue of scoped tasks, clear evidence, and human ownership at the right points.

• AI-assisted 3D printing: from idea to object with my son

  Published: 27 May, 2026

  • 3 min read

  A small weekend maker project with my son: using an AI agent, parametric CAD, and a 3D printer to turn a hanging solar bulb into a desk light stand.

• Warp as an ACP Client

  Published: 17 May, 2026

  • 3 min read

  An experimental prototype of Warp running as an Agent Client Protocol client, separating the terminal UX from the user-owned agent runtime.

• The next AI interface may not be a chatbot

  Published: 12 May, 2026

  • 2 min read

  Chat is useful, but the next layer of AI interfaces may be dynamic workspaces that adapt to the task.

• AI agents need workspaces, not just chat windows

  Published: 28 Apr, 2026

  • 2 min read

  Chat is a useful command layer for AI agents, but it is probably not the final interface. Real work needs state, structure, and rollback.

• AI agents are starting to clean the attic

  Published: 27 Apr, 2026

  • 2 min read

  Some of the best agent work may be the boring cleanup: stale bugs, duplicate issues, old PRs, and half-finished ideas.

• From AI assistants to agentic delivery workflows

  Published: 18 Apr, 2026

  • 2 min read

  The next practical gain in AI-assisted development is moving from one AI helper per developer to shared, issue-driven delivery workflows.

• AI makes demos cheap, not products easy

  Published: 2 Apr, 2026

  • 2 min read

  Agentic development makes impressive demos cheap, but real products still need architecture, ownership, tests, review, and operational discipline.

• Fixing OpenClaw with OpenClaw

  Published: 9 Mar, 2026

  • 2 min read

  A small bug fix felt like an early glimpse of software that can help correct itself, with a human still in the loop.

• AI agent reliability is operations, not prompting

  Published: 2 Mar, 2026

  • 2 min read

  Most agent failures are not solved by prettier prompts. They are solved by verification and institutional learning.