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
- Agentationagentation.dev
- Best practices for coding with agents · Cursorcursor.com
- Why We Built Our Own Background Agentbuilders.ramp.com
- A Guide to Claude Code 2.0 and getting better at using coding agents – sankalp's blogsankalp.bearblog.dev
- AGENTS.mdagents.md
- Agentic Coding Ascension Notes – Machine Learning (Theory)hunch.net
- Agent Observability and Tracingarize.com
- What's Easy Now? What's Hard Now? - Marc's Blogbrooker.co.za
- Cursor: AI coding agentcursor.com
- Vibe-coding limits a creator’s potentialconnieliu.work