{"slug": "data-structure-mate-cutey", "title": "Data Structure Mate cutey", "summary": "A developer built AI Mate, an AI-powered study buddy for learning data structures and algorithms that guides students from brute-force solutions to optimal ones step by step rather than handing over finished code. The tool, built for a Hacktoberfest weekend challenge, uses a backend that attaches a teaching-style prompt to requests sent to the Backboard GPT API, with student level stored in browser localStorage and per-session token limits to control API usage. It also explains real-world applications of each data structure and generates short quizzes after explanations.", "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\n## \n  \n  \n  What I Built\n\n**AI Mate** is an AI-powered study buddy for learning Data Structures and Algorithms (DSA).\n\nMany students struggle with DSA, not because the topics are impossible, but because nobody explains *why* a solution works. AI Mate fixes that:\n\n- \n**Brute force to optimal:** Paste your worst-case solution and AI Mate walks you toward the optimal one, step by step, instead of just dumping the final code.\n- \n**Real-world applications:** For every topic (Arrays, Strings, Linked Lists, Stacks, Queues, and more), it explains where that data structure is used in real software.\n- \n**Level-based learning:** You pick your DSA level when you sign up (beginner, intermediate, advanced), and the explanations match it.\n- \n**Built-in quizzes:** After each explanation, AI Mate gives you short quizzes so you can check whether the concept actually stuck.\n\nI built this for [my friend / classmates / juniors, fill in who] who kept copy-pasting ChatGPT answers and still couldn't explain their own code in interviews.\n\n## \n  \n  \n  Demo\n\n🎥 [Watch the demo video](https://drive.google.com/file/d/1fMxErds0lXwllpFqe4cmwTGufl0NEMDR/view?usp=sharing)\n\n**Typical flow:**\n\n1. A student opens the website and logs in.\n2. They select their DSA level.\n3. They chat with **DSA Mate** : ask about a topic, paste a brute-force solution, or request a quiz.\n4. AI Mate explains, optimizes, and quizzes them.\n\n## \n  \n  \n  Code\n\n🔗 [GitHub Repository](https://github.com/ThakuraAnki/Low_Level_design_Practice_PlateForm)\n\n## \n  \n  \n  How I Built It\n\n**Architecture (high level):**\n\n- \n**Frontend:** The login screen, level selection, and chat interface. Student details (name, level) are stored in the browser's**localStorage** , so there's no heavy database setup for a weekend build.\n- \n**Backend:** A dedicated backend folder receives chat requests, attaches a teaching-style prompt, calls the**Backboard GPT API** , and returns the response to the frontend. This also keeps the API key off the client.\n- \n**Prompt design:** The system prompt tells the AI to behave like a teacher: explain the intuition first, show the brute-force approach, identify the bottleneck, then guide toward the optimal solution, and finally offer a quiz.\n- \n**Token limits:** To control API usage, each student session has a token limit. This is a known limitation, and I'd like to improve it.\n\n**Challenges I faced:**\n\n- Getting the AI to *teach* rather than just answer took a lot of prompt iteration.\n- Balancing response quality against token limits.\n- [Add one real challenge you hit.]\n\n**What I'd add next:**\n\n- Persistent accounts with a real database\n- Progress tracking and weak-topic detection\n- Code execution to test optimized solutions\n- Support for Trees, Graphs, and Dynamic Programming\n\n## \n  \n  \n  Why Does Open Innovation Matter?\n\nMost students go straight to a chatbot, copy the solution, and move on. They get answers but not understanding.\n\nOpen innovation lets small builders like me take powerful public AI APIs and shape them for a specific, real problem. AI Mate doesn't replace the learning process; it works like a good teacher. It tells the whole story behind the code, shows why the brute force is slow, and quizzes you to confirm you understood. Anyone can fork it, change the prompts, and adapt it for their own classmates or subject.\n\n## \n  \n  \n  My Agent Session\n\n[Add your DevRelay session link or `agent_session` embed here, or delete this section if you didn't use one.]\n\n## \n  \n  \n  Prize Categories\n\nBest Use of Backboard\n\nBuild with R-CLI, Backboard's open-source terminal coding agent, compare open-weight models through a single Backboard API key, or give an open-source project's assistant memory and RAG.", "url": "https://wpnews.pro/news/data-structure-mate-cutey", "canonical_source": "https://dev.to/ankit_thakur_d54323e1ae70/data-structure-mate-cutey-3f2b", "published_at": "2026-10-05 02:34:38+00:00", "updated_at": "2026-10-05 02:42:33.430758+00:00", "lang": "en", "topics": ["ai-products", "ai-tools", "generative-ai", "large-language-models"], "entities": ["AI Mate", "Backboard", "Backboard GPT API", "Hacktoberfest", "GitHub"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/data-structure-mate-cutey", "markdown": "https://wpnews.pro/news/data-structure-mate-cutey.md", "text": "https://wpnews.pro/news/data-structure-mate-cutey.txt", "jsonld": "https://wpnews.pro/news/data-structure-mate-cutey.jsonld"}}