To-Do List Agent
by Alexey Grigorev
A reference project from the AI Engineering Buildcamp: an agent that interacts with a simple to-do list application. Built with Lovable for the frontend and FastAPI (Python) for the backend. Uses the backend's OpenAPI spec so the model can create tools to get tasks or mark them complete, with Logfire for monitoring and pytest for testing.
Reference project from the first cohort of the AI Engineering Buildcamp, built to help students understand the requirements for a robust, end-to-end AI application.
The agent does not use RAG or a knowledge base. Instead, it relies on the backend's OpenAPI specification: the spec is fed to the model so it can create tools to get tasks or mark them as complete. Monitoring is done with Logfire, which tracks the entire session, including the specific tools used and the cost of each interaction. The project includes 18 pytest tests covering different scenarios, such as checking whether the right tool is invoked when asking about today's tasks.
Tech stack: Lovable (frontend), FastAPI (Python backend), OpenAPI, Logfire, pytest.
Related content
AI Data Cleaning Assistant
A production-style app that automates messy CSV cleanup: upload a file, profile it, generate AI-backed cleaning steps, apply deterministic transformations, and download a cleaned …
December 15, 2025
Build and Deploy a Full-Stack App with AI Coding Assistants
In this workshop we'll build the classic Snake game as a full-stack web app, end to end. A coding assistant does most of the work. We'll: generate a React frontend with Lovable wr…
June 23, 2026
Test Project
Build a research assistant that uses multiple specialized agents — a searcher, a summarizer, and a fact-checker — coordinated by an orchestrator agent. Learn agent communication p…
March 25, 2026