Skip to content
Youlong MaSoftware engineerLet's talk
All work

Project 01 / Agents + education

EduAgent

A conversation that becomes a learning path.

Contribution

Project development

Explore the original
Project documentation Source code
Study 01 / Abstract interpretationTwo paths negotiate a shared direction, then unfold into a sequence of lessons.

01 / Context

The starting point.

A learning goal is a starting point, not a syllabus. EduAgent explores how multiple agents can work together to turn that goal into a structured learning experience.

02 / Approach

How the pieces connect.

An Analyst and a Planner debate a personalized path before producing a syllabus. An Instructor then teaches each section interactively. Planning and instruction are distinct parts of the same experience.

  1. 01Learning goal
  2. 02Analyst ↔ Planner
  3. 03Syllabus
  4. 04Instructor
Progress is persisted to SQLite. A conceptual reading of the project, not a complete deployment diagram.

03 / In focus

A path with memory

Progress is persisted to SQLite, connecting the learning plan to an ongoing record of study. Pydantic and Pytest sit alongside LangGraph and LangChain in the project’s Python stack.

  • Python
  • LangGraph
  • LangChain
  • OpenAI
  • SQLite
  • Pydantic
  • Pytest

04 / Outcome

What came together.

The project combines collaborative planning, a structured syllabus, interactive instruction, and persisted progress. Its documented test suite contains 99 automated tests.

Read the project documentation
Next connection / 02Agentic Doc Retrieval