
Action Planner AI is an intelligent multi-agent system that transforms how projects move from concept to launch. Powered by GPT-5 for advanced reasoning and LangChain for orchestration, it unites three core agents—Researcher, Planner, and Producer—into a seamless pipeline. The Researcher surfaces credible insights, risks, and references in seconds. The Planner structures milestones and workflows. The Producer converts these into tangible outputs such as blogs, landing pages, GitHub starter kits, YouTube scripts, and campaigns. Together, they eliminate tool fragmentation and deliver ready-to-publish assets in one flow. We validated GPT-5’s potential by testing its reasoning depth, cross-agent collaboration, and asset creation across creative and technical tasks. Using JSON handoffs and LangGraph-powered orchestration, Action Planner ensures precision, cohesion, and reliability in multi-agent communication—avoiding the “hallucination handoffs” common in AI pipelines. Unlike competitors like Copy.ai, Perplexity, Webflow, or vidIQ, which focus on narrow functions, Action Planner AI integrates research, planning, and production into a single ecosystem. It produces not only marketing copy or layouts but an entire launch strategy—credible research, structured milestones, optimized landing pages, cross-channel content, and repositories. This all-in-one approach reduces tool fatigue, saves cost (users avoid paying $100+ monthly for multiple tools), and empowers both creators and innovators to focus on vision rather than mechanics. Built with GPT-5, LangChain, LangGraph, and a Streamlit UI, our platform is scalable and intuitive, designed for the booming creator economy and technical innovators alike. Our vision extends beyond the hackathon: advanced customization, global multi-language support, direct publishing integrations, and vertical modules for domains like e-commerce and software development. Action Planner AI = More Value, Less Cost, Complete Innovation.
24 Aug 2025
.png&w=828&q=75)
The application utilises the Llama-3.3-70b-versatile model for analysis of the upload and download speeds, along with latency and bandwidth of a given region, and predicting the development score based on these parameters. The model further builds on it by suggesting improvements based on priority and condition of network in that region, while also providing detailed steps on how to achieve the desired target. RAG was implemented in order to enhance the performance of the model, which added great value in the performance of the model and helped us achieve much accurate and relevant results. CSV file with over 13000 unique instances of data was utilised for tuning the model for accurate results.
26 Jan 2025

Smartstudy is the next student companion! It is an AI-powered application, which has the following capabilities: - Summarise content - Generate questions and answers from given content - Generate quizzes - Explain and debug code The application utilises the Granite model to provide these services. Tuning to specific prompts and datasets has allowed better and relevant performance, along with a robust UI, where Python has been utilised to give the user a simple but rich experience while accessing the application. In order to connect the application to relevant models, Python has been utilised for data handling and transfer. The ability of the application to read different files, as well as code debugging and generation make it a complete package, with options of quiz generation making it a complete preparation package. Future goals with respect to this application include adding features that enhance user experience, such as text-to-speech generation, multi lingual capabilities and diagram generation to name a few.
26 Aug 2024