Build an agent loop a small model can finish
builder.io
A small coding agent loop was used to repair Agent-Native Figma and slide imports by repeatedly applying fixes until an automated verifier said the output was close enough to the originals. The first job drove mismatches from 88% of pixels off to 2% over one weekend using OpenAI’s smaller model on ChatGPT Pro. A second loop was built that isolates which parts of the process matter, showing that most effort goes into the grading check (its tolerances, examples, and what counts), while a smaller model can handle the repeated grinding once the check is reliable.
Why it matters
A reliable agent loop depends less on model size than on a trustworthy check that turns progress into a score or pass condition. In two visual tasks, small models improved dramatically when they received repeatable feedback across varied examples and holdout cases.