Skip to content

brighthive/brighthive-ai-engineer-excercise

Repository files navigation

🧪 Brighthive AI Agent Engineer Technical Exercise

Welcome to the Brighthive AI Agent Engineer challenge. You'll simulate a SaaS platform that integrates with a metadata catalog and a warehouse, then build a multi-agent workflow using LangGraph to extract, validate, and summarize metadata issues.

🧭 Your Mission

  • Simulate a SaaS integration layer (MCP + warehouse).
  • Build 3 LangGraph agents: MetadataAgent, ValidationAgent, SummaryAgent.
  • Expose a FastAPI endpoint to run the workflow and return a structured report.

🚀 How to Run

  1. Install dependencies (in a virtual env or conda):
pip install -r requirements.txt
  1. Run the API server:
uvicorn saas_layer.service:app --reload
  1. POST to http://localhost:8000/run-workflow
curl -X POST http://localhost:8000/run-workflow

✅ Evaluation Criteria

Area What We're Looking For
Correctness Output is logically accurate
Modular Agent Design Reusable, testable agent logic
Integration Thinking Realistic SaaS/MCP-style structure
Code Quality Clear structure, naming, formatting
Initiative (Bonus) Error handling, testing, extensions

⏱ Time Limit

You should be able to complete this in ~2 hours.

Good luck!

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages