Running AWS Strands Decider 2B Locally: A Complete Setup Guide for AI Routing & Multi-RAG Systems

A developer documented a step-by-step process for installing and running AWS's Strands Decider 2B, a lightweight decision model for routing, classification, scoring, and agent orchestration, locally on Windows via WSL2. The guide covers setting up a Python virtual environment, installing the strands-decider package, serving the StrandsAgents/strands-decider-2B-hobson-v19 model on CPU, and calling its REST endpoint with choice, yes/no, and score decision formats. A sample choice query returned a "PLM" selection with 0.94 confidence, illustrating how a dedicated decision model can handle routing so an LLM focuses on reasoning and generation.

As GenAI applications become more sophisticated, one challenge continues to surface: How do we make reliable decisions before invoking an LLM? For example: Traditionally, we let an LLM make these decisions. Recently, AWS introduced Strands Decider 2B , a lightweight decision model designed specifically for routing, classification, scoring, and orchestrating agent workflows. Unlike traditional LLMs, Strands Decider doesn't generate arbitrary text. Instead, it selects from predefined options and provides confidence scores, making it ideal for Agentic AI and Multi-RAG systems. In this article, I'll walk through how I installed and tested Strands Decider 2B locally on Windows using WSL2. A common architecture today looks like this: The problem? The LLM is responsible for both: A better approach is: Now the LLM focuses on reasoning and generation, while the decision model handles routing and orchestration. For this walkthrough I used: Open PowerShell: wsl -l -v Example output: NAME STATE VERSION Ubuntu Running 2 Launch Ubuntu: wsl -d Ubuntu mkdir -p /mnt/c/GENAI/strands cd /mnt/c/GENAI/strands Update Ubuntu: sudo apt update Install required dependencies: sudo apt install -y \ python3 \ python3-pip \ python3-venv \ python3-dev \ build-essential \ gcc \ g++ Create the environment: python3 -m venv .venv Activate it: source .venv/bin/activate Upgrade pip: pip install --upgrade pip setuptools wheel pip install strands-decider Verify installation: strands-decider --help Install Hugging Face Hub: pip install huggingface hub List available Strands models: python python -c "from huggingface hub import list models; print m.id for m in list models search='strands' " The model used in this guide: StrandsAgents/strands-decider-2B-hobson-v19 Launch the model: strands-decider serve StrandsAgents/strands-decider-2B-hobson-v19 --device cpu Expected output: Application startup complete. Uvicorn running on http://127.0.0.1:8000 The first startup downloads and caches the model automatically. Open in your browser: http://127.0.0.1:8000/docs Or: curl http://127.0.0.1:8000/openapi.json Strands Decider supports three decision formats. Choose one option from a list. { "type": "choice", "instructions": "Select the best datasource.", "criteria": { "PLM": "Engineering changes and parts", "JIRA": "Issue tracking system", "CONFLUENCE": "Documentation repository", "UNKNOWN": "No suitable source" } } Yes / No decision. { "type": "noul", "instructions": "Determine whether this statement is true." } Rate against an ordered scale. { "type": "score", "instructions": "Rate the sentiment.", "criteria": "Very Negative", "Negative", "Neutral", "Positive", "Very Positive" } Create a file called: decider demo.py python import requests import json payload = { "state": "User wants ECO information", "questions": { "datasource": { "type": "choice", "instructions": "Select the most appropriate datasource.", "criteria": { "PLM": "Engineering changes and parts", "JIRA": "Issue tracking system", "CONFLUENCE": "Documentation repository", "UNKNOWN": "No suitable source" } } } } response = requests.post "http://127.0.0.1:8000/v1/systemone", json=payload print json.dumps response.json , indent=2 Run: python decider demo.py Sample output: { "answers": { "datasource": { "choice": "PLM", "confidence": 0.94 } } } One use case I was particularly interested in was reducing hallucinations across multiple RAG systems. Routing logic becomes simple: decision = response "answers" "datasource" "choice" if decision == "PLM": plm rag.search query elif decision == "JIRA": jira rag.search query elif decision == "CONFLUENCE": confluence rag.search query else: print "No reliable datasource identified." Instead of asking an LLM to guess which datasource to use, the decision model handles routing first. I see strong potential in the following scenarios: ✅ Multi-RAG orchestration ✅ Agent tool selection ✅ Engineering Change workflows ✅ PLM assistants ✅ SharePoint routing ✅ Confluence routing ✅ Jira ticket management ✅ Intent classification ✅ Confidence-based validation ✅ Hallucination reduction One of the biggest lessons I've learned building GenAI applications is: Not every problem requires text generation. Decision-making and text generation are fundamentally different tasks. Using a decision model before retrieval and generation creates a much cleaner architecture: Decision Model ↓ Retrieval ↓ LLM For enterprise AI systems, agentic workflows, and multi-RAG architectures, this pattern improves reliability, control, and observability. If you're building AI agents today, I highly recommend experimenting with decision models as part of your architecture. Repository: https://github.com/ujjwalbsoni/strands-decider-end-to-end https://github.com/ujjwalbsoni/strands-decider-end-to-end Ujjwalkumar Soni Passionate about AI Agents, RAG Architectures, Knowledge Management, and Enterprise GenAI Solutions. Let's connect and share ideas around Agentic AI and next-generation enterprise applications.