The pixel is the last unchecked artifact in agentic coding. applitools shipped eyes visual ai mcp…
the pixel is the last unchecked artifact in agentic coding. applitools shipped eyes visual ai mcp tools on september 15, wiring deterministic visual checks into claude code, cursor, copilot and cline so agents maintain baselines and diff layouts themselves.
the agent now reviews its own screens.
Context
Applitools' what's new page has an entry dated 15 September 2026, New Tools in the Eyes MCP Server. It says a coding agent paired with the Eyes MCP server could already add visual tests and can now inspect, review and resolve them, pull pixel-accurate diff evidence and DOM context, and accept, reject or mask baselines from chat, working from Claude Code, Cursor, Copilot, Codex and other AI coding agents. Other 15 September entries cover NLP test steps and a Figma design baselines integration.
The 15 September release is first-party and vendor-reported. Cline is not named in the text read; Codex is. Deterministic in the page attaches to the language model for NLP test steps, while the MCP entry says pixel-accurate diff, so deterministic visual checks is the note's wording. Agents maintain baselines themselves is autonomy wording not in the text, which says the agent can accept, reject or mask baselines. The last unchecked artifact is the author's claim, with no evidence seen.
Watch next
- The MCP docs page's full list of supported agents and independent false-positive testing.
Sources
- What's new (Applitools)applitools.com
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 21 September 2026 at 10:06 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →