Built a LangChain-based agentic application that turns a learning goal into a structured, personalised learning plan.

The application supports two execution modes:

⚡ ReAct Agent Mode A tool-using agent dynamically selects custom tools for course lookup, completion-time calculation, and learning-plan generation.

🔍 Explain Mode — LCEL A deterministic LCEL pipeline executes the planning workflow step-by-step, making the process more transparent, predictable, and easier to debug.

The project also uses Pydantic structured outputs, Groq, Python, Streamlit, and custom LangChain tools, with deterministic logic kept outside the LLM wherever possible.

This project was built to explore the practical engineering side of AI agents — tool calling, agent orchestration, structured outputs, deterministic workflows, and explainability.

The project is not currently deployed, but the complete source code and implementation are available on GitHub.

Tech: Python · LangChain · ReAct · LCEL · Groq · Pydantic · Streamlit

turning a learning goal into an actual plan is such a useful agent use case 🔥

Built an AI-powered Social Media Post Analyzer that analyzes social media content and generates structured insights using LLMs.

The application uses LangChain and Pydantic to process the input and return structured results through an interactive Streamlit interface.

Built with: Python, LangChain, Pydantic, Hugging Face, Streamlit, and LangSmith.

Pydantic catches shape errors, but a plausible wrong insight can still pass. I'd keep a small set of posts with expected labels in LangSmith and rerun it after prompt changes. Are you tracking that kind of drift?