What you can do with Strands Decider

4 use cases

• Route support messages to the right team

  Pick the owning team for an incoming message, with a confidence score on the choice.

  • Strands Decider
  • Work and operations
  • Intermediate
  View prompt

  Using the strands-decider repo, run the ask command with --state set to <message text> and a --choice question listing the team names <teams>. Return the chosen team and its confidence. Verify that the confidence is a number between 0 and 1 and that the chosen team is one of the listed options.

  Share Save

• Flag messages that convey urgency

  Get a yes or no urgency check on each message from a single command.

  • Strands Decider
  • Work and operations
  • Beginner
  View prompt

  Using the strands-decider repo, run the ask command with --state set to <message text> and --noul set to "Does this convey urgency?". Return the noul value. Verify that the value is between 0 and 1 and that a clearly urgent test message scores higher than a routine one.

  Share Save

• Serve a scorer that other services can call

  Run the decision model as a local HTTP server and send it questions with curl.

  • Strands Decider
  • Work and operations
  • Intermediate
  View prompt

  Using the strands-decider repo, start the server with the 2B model on port 8000, then POST a state of <text> and a score question to /v1/systemone. Return the score and confidence from the JSON response. Verify that the response contains an answers object and a latency_ms field.

  Share Save

• Check a form image for a filled-in field

  Ask a yes or no question about an image, such as whether a signature block is filled in.

  • Strands Decider
  • Work and operations
  • Advanced
  View prompt

  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.

  Share Save

How to use Strands Decider

1. Check you have what it needs: 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.
2. Open strands-labs/strands-decider on GitHub and read the README and license.
3. pip install strands-decider
4. strands-decider ask StrandsAgents/strands-decider-2B-qwen3.5-v1-2610 --state "Help! My payouts have been failing for 3 days! " --choice "Which team should handle this?=billing,sales,retail" (inferred, check the README)
5. Read the line that starts with choice_0 and the confidence in brackets.
6. Send answers at confidence 0.9 or more straight through. Send lower ones to a person to confirm.

These steps come from our top use case, Route support messages to the right team, which also has a copy-paste agent prompt.

Strands Decider alternatives · Best AI repos for Work and operations

About this repo

• Who it is forDevelopers and agent builders who need quick, cheap classification or scoring inside an agentic workflow, without training a classifier.
• Why it is hot
• LanguagePython
• Sourcegithub.com/strands-labs/strands-decider · Back to Hot repos

Requirements

• 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

Related repos

• #4 this week AI Job Search An open-source framework built on Claude Code that runs a job search on your own machine: it evaluates postings, tailors CVs and cover letters, and preps interviews.
• #7 this week Solidcraft SolidCraft is an open-source parametric 3D CAD application written in pure Rust, with desktop, browser, headless CLI and MCP server versions.
• Trended earlier Fastbrowse fastbrowse is a Python browser agent where a choice model picks each action from the controls on a page, and answers come back with verbatim quotes from that page.