You can tell Claude to verify its work. I’m using it for data analysis tasks and I always have it check the raw data for accuracy. It was a whole different ballgame when I started doing that.
Clear instructions go a long way, asking it to review work, asking it to debug problems, etc. definitely helps.
Definitely - with ONE pretty big callout. This only works when a clear and quantifiable rubric for verification can be expressed. Case in point, I put Claude Code to work on a simple react website that needed a "Refresh button" and walked away. When I came back, the button was there, and it had used a combination of MCP playwright + screenshots to roughly verify it was working.
The problem was that it decided to "draw" a circular arrow refresh icon and the arrow at the end of the semicircle was facing towards the circle centroid. Anyone (even a layman) would take one look at it and realize it looked ridiculous, but Claude couldn't tell even when I took the time to manually paste a screenshot asking if it saw any issues.
While it would also be unreasonable to expect a junior engineer to hand-write the coordinates for a refresh icon in SVG - they would never even attempt to do that in the first place realizing it would be far simpler to find one from Lucide, Font Awesome, emojis, etc.
In general, using your own symbol forms for interactions rather than taking advantage of people’s existing mental models is a bad idea. Even straying from known libraries is shaky unless you’re a competent enough designer to understand what specific parts of a visual symbol signify that specific idea/action, and to whom. From a usability perspective, you’re much better off not using a symbol at all than using the wrong one.
I second this and would add that you really need an automated way to do it. For coding, automated test suites go a long way toward catching boneheaded edits. It will understand the error messages from the failed tests and fix the mistakes more or less by itself.
But for other tasks like generating reports, I ask it to write little tools to reformat data with a schema definition, perform calculations, or do other things that are fairly easy to then double-check with tests that produce errors that it can work with. Having it "do math in its head" is just begging for disaster. But, it can easily write a tool to do it correctly.
Clear instructions go a long way, asking it to review work, asking it to debug problems, etc. definitely helps.