{
  "id": 11583948,
  "title": "Running AWS Strands Decider 2B Locally: A Complete Setup Guide for AI Routing & Multi-RAG Systems",
  "url": "https://urgent.news/2026/10/03/running-aws-strands-decider-2b-locally-a-complete-setup-guide-for-ai",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-03T02:33:20.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/ujjwalbsoni/running-aws-strands-decider-2b-locally-a-complete-setup-guide-for-ai-routing-multi-rag-systems-249c"
  },
  "original_language": "en",
  "account": "Running AWS Strands Decider 2B Locally for Multi-RAG and Agentic AI Applications\n\nMaking reliable decisions before invoking a large language model (LLM) remains a challenge as GenAI applications grow more sophisticated. AWS has addressed this with Strands Decider 2B, a lightweight decision model focused on routing, classification, scoring, and orchestrating agent workflows. This setup guide outlines the process of installing and testing Strands Decider 2B locally on Windows using WSL2.\n\nWhy Use a Decision Model?\nTraditionally, LLMs handle both decision-making and response generation, leading to inefficiencies. By separating concerns, the LLM focuses on reasoning and generating responses, while the decision model takes care of routing and orchestration.\n\nPrerequisites\nThe guide assumes the following environment:\n- Windows 11\n- WSL2 Ubuntu\n- Python virtual environment\n- Strands Decider 2B\n\nInstallation Steps\n1. Verify WSL2 Installation\n- Open PowerShell and run: wsl -l -v\n- This confirms that WSL2 is properly installed and running.\n\n2. Create a Workspace Directory\n- Open a terminal and execute: mkdir -p /mnt/c/GENAI/strands\n- This creates a dedicated directory for the project.\n\n3. Install Required Packages\n- Update Ubuntu: sudo apt update\n- Install dependencies: sudo apt install -y python3 python3-pip python3-venv python3-dev build-essential gcc g++\n\n4. Create a Virtual Environment\n- Create the environment: python3 -m venv .venv\n- Activate it: source .venv/bin/activate\n- Upgrade pip: pip install --upgrade pip setuptools wheel\n\n5. Install Strands Decider\n- Run: pip install strands-decider\n- Verify installation by executing: strands-decider --help\n\n6. Discover Available Models\n- Install Hugging Face Hub: pip install huggingface_hub\n- List available Strands models using: python -c \"from huggingface_hub import list_models; [print(m.id) for m in list_models(search='strands')]\"\n- The specific model used in this guide: StrandsAgents/strands-decider-2B-hobson-v19\n\n7. Start the Model Server\n- Launch the model with: strands-decider serve StrandsAgents/strands-decider-2B-hobson-v19 --device cpu\n- Expected output: Application startup complete. Uvicorn running on http://127.0.0.1:8000\n- Note that the first startup downloads and caches the model automatically.\n\n8. Verify the API\n- Open a web browser and navigate to http://127.0.0.1:8000/docs\n- Alternatively, use curl to check the OpenAPI specification: curl http://127.0.0.1:8000/openapi.json\n\nUnderstanding Question Types\nStrands Decider supports three decision formats:\n1. Choice Question: Choose one option from a list.\n- Type: choice\n- Instructions: Select the best datasource.\n- Criteria:\n- PLM: Engineering changes and parts\n- JIRA: Issue tracking system\n- CONFLUENCE: Documentation repository\n- UNKNOWN: No suitable source\n\n2. Noul Question: Yes/No decision.\n- Type: noul\n- Instructions: Determine whether this statement is true.\n\n3. Score Question: Rate against an ordered scale.\n- Type: score\n- Instructions: Rate the sentiment.\n- Criteria:\n- Very Negative\n- Negative\n- Neutral\n- Positive\n- Very Positive\n\nTesting with Python\nCreate a file called decider_demo.py with the following content:\n```python\nimport requests\nimport json\n\npayload = {\n\"state\": \"User wants ECO information\",\n\"questions\": {\n\"datasource\": {\n\"type\": \"choice\",\n\"instructions\": \"Select the best datasource.\"\n}\n}\n}\n```\nThis payload represents a choice question where the user wants ECO information and needs to select the best datasource.",
  "summary": "🚀 Running AWS Strands Decider 2B Locally for Multi-RAG and Agentic AI Applications As GenAI applications become more sophisticated, one challenge continues to surface: How do we make reliable decisions before invoking an LLM? For example: Which datasource should answer this question? Should I query PLM, Jira, or Confluence? Do I have enough context to answer confidently? Should an AI agent…",
  "key_points": [
    "Strands Decider 2B installed locally on Windows using WSL2",
    "Supports three decision formats: Choice, Noul, and Score questions",
    "Tested with Python script creating choice question payload"
  ],
  "editors_take": "Separating decision-making from response generation with Strands Decider 2B allows large language models to focus on reasoning, improving efficiency in GenAI applications by offloading routing and orchestration tasks.",
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}