Reading plates off photos by hand is slow and error-prone, especially at volume. This pulls the plate from each form-uploaded image automatically.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Read the license plate characters with a vision model, including the region where visible.
pending
Normalize the plate string and note a confidence level for the read.
pending
Write the plate, timestamp, and confidence to a Sheet and flag low-confidence reads for review.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Read the license plate from the photo; return JSON with the plate string, region, and a confidence score from 0 to 1.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.