Who it is forAn operations or document-review person who needs to confirm that scanned pages have a specific field completed.
The problemChecking many scanned pages by eye takes time, and a text-only model cannot see the page.
The outcomeEach page gets a noul score for the question, so pages that fail the check can be sent back for review.
What you need first
- Python with pip to install the strands-decider package
- A machine that can run a 2B model: a CUDA GPU, an Apple-silicon Mac, or CPU
- Text inputs you want to classify, route, or score
Steps
pip install "strands-decider[vision]"- Install transformers 5.18 or later, as the README requires for vision.
strands-decider ask StrandsAgents/strands-decider-2B-qwen3.5-v1-2610 --state "" --image page.png --noul "Is the signature block filled in?"(inferred, check the README)- Review pages with low scores by hand.
Prompt for your agent
Using the strands-decider repo with the vision extra installed, run the ask command on <image path> with a noul question about <field>. Return the noul value. Verify the result on two known pages, one filled in and one blank, before trusting the scores.
Caveat. The README says the vision support works with the published checkpoints without image training, and that the Gemma 4 models read text only, so use the Qwen3.5 model for images.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page