Annotating for agents
benji.org · 556 words · saved by 5 readers
The gap between seeing and describing.
16 January, 2026 AI coding tools have gotten increasingly good at understanding visual feedback. Some take an all-in-one approach: v0, Lovable, Bolt, and Cursor's visual editor let you select elements directly and iterate on what you see. Others, like Claude Code, are more flexible but rely on screenshots and descriptions. There's often a tradeoff: point at elements but stay locked in, or use any tool but describe everything in text. This problem becomes especially obvious when working on animations and interactions, which is what got me thinking about how to give better visual feedback to…
saved by
related reading
- Agentationagentation.dev
- Agentationagentation.com
- Agentic Coding Ascension Notes – Machine Learning (Theory)hunch.net
- Agentationagentation.dev
- Why We Built Our Own Background Agentbuilders.ramp.com
- Demystifying evals for AI agents \ Anthropicanthropic.com
- Thoughts on slowing the fuck downmariozechner.at
- Code was our medium for thoughtwattenberger.com
- Building Effective AI Agents \ Anthropicanthropic.com
- Don’t Outsource Your Thinkingteltam.github.io
- Understanding is the new bottleneckgeoffreylitt.com
- The Unreasonable Effectiveness of Agentic Loopsweb.navan.dev