Scrawl: a new tool for effectively critiquing AI agent outputs in design workflows
gregbarbosa · x · 2026-10-19
Developer kitlangton shares his thinking on optimizing the feedback loop between humans and AI agents — both how to steer and view their outputs, and how to critique them effectively. Scrawl is his attempt at solving the critique side, and he's "extremely happy" with it. Another developer says he'll try it at work today while using agents to speed through design iterations and workflows.
More from coding & agent
- Greptile raises $50M Series B at $750M valuation, reviews 1% of all GitHub PRs — Rasmic · 2026-10-19
- Do you still review every UI change by hand when an agent writes it? — mfbzme · 2026-10-19
- Dev builds playable Tesla Roadster web game in a weekend with Opus 5.5 — edwinarbus · 2026-10-19
- Blender renders cut from 4 hours to minutes with Opus 5.5 and cloud GPUs — ravisparikh · 2026-10-19
- LangChain Hosts Life Sciences Agent Engineering Workshop: Build, Trace, Evaluate Research Agents — LangChain · 2026-10-19
- Librarian Agents: new paper lets agents curate their own long-context workspaces — charles_irl · 2026-10-19