AI-SDLC Multi-Agent Framework

A LangGraph framework at TietoEvry where one supervisor agent coordinates specialised agents for requirement analysis, code generation, peer review, unit tests and documentation.

Stack

LangGraph, LangChain, Python, FastAPI, Azure OpenAI, GitHub Copilot, REST

Problem

One framework where requirement analysis, code generation, review, unit tests and documentation are each an agent, and a single supervisor owns the result.

Interface

Illustrative interface

Pull request #218feature/export-rate-limitApproved

Add a rate limit to the export endpoint

5 agents · 1 supervisor

Requirements

Limit the export endpoint to 10 requests per minute per user. Over the limit, return 429 with a Retry-After header.

Keyed on user, not IP
429 carries Retry-After

Unit tests

tests/test_export.py6 passed

Docs

docs/api/export.md

429 response documented

Code genapi/routes/export.py+3 −1

1414 @router.get("/export")
15-async def export(user=Depends(current_user)):
15+@limiter.limit("10/minute", key=user_key)
16+async def export(request: Request,
17+ user=Depends(current_user)):
1618 return await build_export(user)

Peer review

Keys on the user id, so a shared office IP is not throttled as one. Retry-After matches the window. Approve.

Architecture

What I built

A supervisor agent on LangGraph that coordinates the specialised agents.
Specialised agents for requirement analysis, code generation, peer review, unit test creation and documentation.
Each agent is an independent LangGraph node with its own custom skills and tool calling.
GitHub Copilot custom agents, skills and hooks, with FastAPI REST services around the framework.
Presented to senior leadership as part of the entry that won 1st prize at TietoEvry TechUtsav 2025.

Proof

1st prize, TietoEvry TechUtsav 2025 (with EVA and enterprise GenAI demos)

Stack

LangGraph
LangChain
Python
FastAPI
Azure OpenAI
GitHub Copilot
REST

Share this case

LinkedIn WhatsApp