Skip to content
← All projects
GenAI / Coding ToolsPrototype

Multi-Agent DSA Interview Assistant

A Streamlit assistant where 6 specialized LLM agents collaborate to plan, brute-force, optimize, generate, review, and explain DSA interview solutions.

Overview

A multi-agent coding-interview assistant where specialized agents plan, generate, review, and explain DSA solutions.

A strong supporting GenAI project once deployment and dependency cleanup are complete.

Impact

  • LangGraph pipeline with a reviewer-to-code-generator retry loop capped at 3 attempts over shared typed state.
  • Renders each reasoning stage in the UI so users can follow the problem-solving process.
  • Deployment, dependency pinning, and README polish remain planned.

What it shows

  • Typed shared state and multi-step agent coordination.
  • Reviewer feedback loops with bounded retries.
  • A visible reasoning-stage UI that helps users learn the problem-solving process.

Demo plan

  • Deploy a Hugging Face Space with a small curated problem set and predictable model settings.
  • Add screenshots or a short video for cases where the model provider is slow.

Stack