When I paste a screenshot into Claude Code or Cursor, a crop plus an arrow usually fixes the "where." What kept going wrong for me was the "why" once there are three or four things to fix on one screen.
What helped was talking while I draw. I circle a clipped label and say "let this wrap," then draw an arrow to a chart point and say "tooltip on hover and keyboard focus." Lasso puts [1] and [2] in the transcript at the exact words I said while making each mark. So the agent gets numbered marks with my intent attached, instead of a paragraph it has to match back to the image.
I also stopped pasting. A local coding agent on the same Mac can pull the latest annotated capture or voice brief itself through Lasso's local MCP server, and Lasso asks before the first agent call.
I wrote up the full workflow, with an example prompt for a UI fix, here: https://www.trylasso.online/guid...
love this concept... sometimes a quick circle or arrow explains more than a whole paragraph.
the local MCP server makes it even more interesting.
Great work! 💪
@david_takidze Glad you liked it! Would love to hear feedback in the future
local mcp. can cursor see the circle if lasso is not the front app?
This is actually pretty cool! Love the idea of just circling something on your screen and letting AI figure out what you're talking about. Any plans to bring this to Windows too?