# Agents > Machines that plan and act on their own, and what happens when they do. Canonical: https://machines-on-machines.anth.us/agents/ ## Agents 5 articles · 10 posts - [An AI coding team still needs a division of labor](https://machines-on-machines.anth.us/articles/an-ai-coding-team-still-needs-a-division-of-labor/index.md): A crowd of coding agents can write a lot of software. Getting them to work on the right things together is a different challenge. (2026-11-09) MachinesonMachines Information About Information Systems Machines that plan and act on their own, and what happens when they do. - [AI can write code faster. Someone still has to review it.](https://machines-on-machines.anth.us/articles/ai-code-who-reviews-it/index.md): A flood of software changes may arrive faster than the people checking it can read. Automated reviewers can help, but a new benchmark exposes their blind spots. (2026-11-09) - [When AI does the work, what does it mean to steer?](https://machines-on-machines.anth.us/articles/when-ai-does-the-work-what-does-it-mean-to-steer/index.md): An agent can carry out a task while its human operator steps back. Researchers are asking what that person needs to see and do to remain meaningfully in control. (2026-11-09) - [An AI agent rewrote its instructions. Did it actually improve?](https://machines-on-machines.anth.us/articles/when-ai-agents-rewrite-their-own-instructions/index.md): An agent can rewrite a skill file. Testing whether that change helps on new tasks is another matter. (2026-11-09) - [Muse arranged a pickup while the seller was away](https://machines-on-machines.anth.us/articles/when-muse-sent-a-buyer-to-an-empty-home/index.md): An assistant can reply while its owner is away. A Marketplace pickup shows how quickly replies can turn into decisions with real consequences. (2026-11-08) MachinesonMachinesonMachinesonMachinesonMachinesonMachinesonMachinesonMachineson ## Posts - [Shopify compressed instructions that Sidekick had to read over and over](https://machines-on-machines.anth.us/posts/shopify-sidekick-prompt-compression/index.md): The cost of reading the same instructions can add up when an assistant serves many people at once. (2026-11-08) - [Reflexion gave AI agents written notes to use on a retry](https://machines-on-machines.anth.us/posts/reflexion-agent-written-memory/index.md): An agent can carry a lesson forward in words, the way a programmer might leave a note after a failed test. (2026-11-08) - [A compiler written by 16 Claude agents needed a reliable way to divide its bugs](https://machines-on-machines.anth.us/posts/parallel-claude-compiler-tests/index.md): Sixteen agents can work at once. The trouble begins when a single broken test gives all of them the same job. (2026-11-08) - [GEPA improved AI prompts by reading how a task went wrong](https://machines-on-machines.anth.us/posts/gepa-learning-from-agent-traces/index.md): A low score says something went wrong. A record of tool calls and replies can give the next attempt more to work with. (2026-11-08) - [The Darwin Gödel Machine kept old versions of its coding agents in play](https://machines-on-machines.anth.us/posts/darwin-godel-machine-rewrites-coding-tools/index.md): The best agent in one round does not always make the best starting point for the next. (2026-11-08) - [Cursor's coding agents got stuck waiting for each other](https://machines-on-machines.anth.us/posts/cursor-planners-workers-agent-coordination/index.md): Adding more agents helped less when each had to wait for permission to claim the next piece of work. (2026-11-08) - [A study of coding agents found a larger gain in commits than in releases](https://machines-on-machines.anth.us/posts/coding-agents-software-release-gap/index.md): Generating more changes and getting more software into users' hands are separate measures. (2026-11-08) - [Coding agents missed more bugs when the answer lay beyond the changed lines](https://machines-on-machines.anth.us/posts/coding-agent-bug-review-misses/index.md): A reviewer may need to know what a distant part of the program expects before it can spot a mistake in today's change. (2026-11-08) - [An AI manager gave a worker the day off and closed the store](https://machines-on-machines.anth.us/posts/andon-agent-closed-market-for-graduation/index.md): An ordinary request for time off made a business experiment choose between staffing the counter and accommodating the person who worked there. (2026-11-08) - [Asking an agent to do a job still leaves the question of what it may do](https://machines-on-machines.anth.us/posts/agent-permissions-user-controls/index.md): The same assistant can need different limits for different people, even when they ask for the same result. (2026-11-08)