{"slug": "social-confidence-coach-a-private-ai-practice-partner-for-my-roommate", "title": "Social Confidence Coach: A Private AI Practice Partner for My Roommate", "summary": "A developer built the Social Confidence Coach, a local Python application that uses Ollama and Meta's open-weight Llama 3.2 1B model to give their roommate a private, zero-stakes way to practice conversations and receive real-time AI feedback. The tool offers three difficulty levels, maintains multi-turn conversation context, and has the model output both in-character dialogue and a brief '[Coach Advice:]' evaluation after each turn. The developer argues that running the model locally keeps sensitive practice conversations on-device and avoids cloud API costs.", "body_md": "*This is a submission for the [Hacktoberfest Weekend Challenge: Build for a Friend](https://dev.to/challenges/hacktoberfest-weekend-2026-10-01)*\n\nI built the **Social Confidence Coach** for my roommate, who struggles with social anxiety, meeting new people, and initiating casual conversations. \n\nApproaching peers or making small talk can feel intimidating and stressful. I wanted to give him a zero-stakes, completely private simulation where he can select different difficulty levels (from low-pressure barista chats to campus conversation starters), practice what to say, and receive real-time constructive feedback from an AI coach on whether his responses are engaging, natural, and polite.\n\nfile:///private/var/folders/zz/ms_5j6rx5q195c7yt3x7k_y40000gn/T/TemporaryItems/NSIRD_screencaptureui_jfvbK3/Screenshot%202026-10-04%20at%206.57.28%E2%80%AFPM.png\n\n``` python\npython\nimport ollama\n\ndef main():\n    print(\"=== Social Confidence Daily Challenge & AI Practice ===\")\n    print(\"Choose your practice scenario:\")\n    print(\"1. Low Pressure - Casual greeting with a barista/cashier\")\n    print(\"2. Medium Pressure - Small talk with a student at a campus cafe\")\n    print(\"3. Active Engagement - Chatting with someone about shared interests\")\n\n    choice = input(\"\\nEnter 1, 2, or 3: \").strip()\n\n    scenarios = {\n        \"1\": \"You are a friendly barista at a local cafe during a quiet afternoon.\",\n        \"2\": \"You are a fellow student sitting at a campus cafe studying for an exam.\",\n        \"3\": \"You are an approachable student sitting in the library reading an interesting book.\"\n    }\n\n    selected_scenario = scenarios.get(choice, scenarios[\"2\"])\n\n    system_instruction = (\n        f\"Roleplay scenario: {selected_scenario} \"\n        \"Keep your in-character answers brief (1 to 2 sentences). \"\n        \"On a brand new line, always write '[Coach Advice:]' and give 1 brief sentence \"\n        \"evaluating whether the user's message was natural, open-ended, or polite.\"\n    )\n\n    messages = [{\"role\": \"system\", \"content\": system_instruction}]\n\n    print(\"\\nScenario started! Type 'exit' to quit.\\n\")\n\n    while True:\n        user_input = input(\"You: \")\n\n        if user_input.strip().lower() == \"exit\":\n            print(\"\\nSession complete. Great practice!\")\n            break\n\n        messages.append({\"role\": \"user\", \"content\": user_input})\n\n        response = ollama.chat(\n            model=\"llama3.2:1b\",\n            messages=messages\n        )\n\n        reply = response[\"message\"][\"content\"]\n        print(f\"\\n{reply}\\n\")\n\n        messages.append({\"role\": \"assistant\", \"content\": reply})\n\nif __name__ == \"__main__\":\n    main()\n\n## How I Built It\nThe application is built in Python and runs locally using the official ollama Python library and Meta’s open-weight Llama 3.2 1B model.\n\nScenario Selection: The user chooses a comfort level, which dynamically constructs a tailored system prompt for the roleplay.\n\nContext Memory: The script maintains a conversation history array (messages), ensuring the open-source model retains context across multi-turn interactions.\n\nDual Role Output: The model is instructed to output both an in-character peer dialogue and an analytical [Coach Advice:] snippet after each turn.\n\n## Why Does Open Innovation Matter?\nOpen innovation and open-weight models are vital for a tool like this:\n\nTotal Privacy for Sensitive Topics: Practicing social interactions, dating openers, and overcoming social anxiety feels deeply personal. Closed cloud APIs store chat logs on remote servers. Running Llama 3.2 locally on a laptop via Ollama ensures that sensitive practice conversations never leave the machine.\n\nOffline & Zero Cost: Social self-improvement tools should not require a recurring credit card charge or active internet connection. Open-source AI makes this available anywhere, completely free of charge.\n\n## My Agent Session\nI developed this project step-by-step with the help of an interactive AI coding assistant. \n\nDuring the build process, the assistant helped me:\n1. Set up the local environment and troubleshoot the `ollama` library installation in VS Code.\n2. Structure the conversation memory loop in Python so the model remembers chat context across multiple turns.\n3. Engineer the dual-response system prompt so the local open-source model reliably outputs both in-character dialogue and actionable coaching advice in every turn.\n\n##Feedback from My Friend\nI had my roommate sit down and test it out by picking Level 2. After trying a couple of openers, his reaction was:\n\n\"It actually feels way less intimidating to test lines here than feeling awkward in person, and the quick tips tell me if I sounded too blunt.\"\n\n## Prize Categories\nPrimary Track: Build for a Friend\n\n<!-- Thanks for participating! -->\n```\n\n", "url": "https://wpnews.pro/news/social-confidence-coach-a-private-ai-practice-partner-for-my-roommate", "canonical_source": "https://dev.to/prashilchaudhary_/social-confidence-coach-a-private-ai-practice-partner-for-my-roommate-1bp9", "published_at": "2026-10-04 13:38:35+00:00", "updated_at": "2026-10-04 13:42:31.513761+00:00", "lang": "en", "topics": ["large-language-models", "ai-tools", "generative-ai", "ai-products"], "entities": ["Ollama", "Meta", "Llama 3.2 1B", "Social Confidence Coach", "Hacktoberfest"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/social-confidence-coach-a-private-ai-practice-partner-for-my-roommate", "markdown": "https://wpnews.pro/news/social-confidence-coach-a-private-ai-practice-partner-for-my-roommate.md", "text": "https://wpnews.pro/news/social-confidence-coach-a-private-ai-practice-partner-for-my-roommate.txt", "jsonld": "https://wpnews.pro/news/social-confidence-coach-a-private-ai-practice-partner-for-my-roommate.jsonld"}}