AI Hackathon Review Platform on AWS

Serverless review platform with a fast read path via FastAPI and DynamoDB, and an async write path using SQS and Lambda....

56 views
Viewed 56 times
0

Create a free account to remix this architecture

Sign up freeor sign in

AI Hackathon Review Platform on AWS

Serverless review platform with a fast read path via FastAPI and DynamoDB, and an async write path using SQS and Lambda. Bedrock-powered judge agents fan out, synthesize results, and store reviews.

advanced
Control Plane — Agent Lane
Strands Review Orchestrator
claude-sonnet-4.5EVENT
4 tools:read_submission, spawn_parallel_judges +2
Orchestrates 5 services
Judge Agent 1
claude-sonnet-4.5EVENT
1 tool:analyze_submission
Orchestrates 1 service
Judge Agent 2
claude-sonnet-4.5EVENT
1 tool:analyze_submission
Orchestrates 1 service
Judge Agent 3
claude-sonnet-4.5EVENT
1 tool:analyze_submission
Orchestrates 1 service
Judge Agent 4
claude-sonnet-4.5EVENT
1 tool:analyze_submission
Orchestrates 1 service
Judge Agent 5
claude-sonnet-4.5EVENT
1 tool:analyze_submission
Orchestrates 1 service
Synthesis Agent
claude-sonnet-4.5EVENT
2 tools:merge_judge_outputs, produce_final_review
Orchestrates 2 services
lambda revi…ddb reviewsqs reviewbedrock llmsecret gith…bedrock llmbedrock llmbedrock llmbedrock llmbedrock llmbedrock llmddb review
AWS

Tags

#serverless
#ai-agents
#aws
#api
#workflow

Architecture Description

You are a solutions architect. Create a clean, high-level system architecture diagram for an AI-powered hackathon review platform.                                  The system has two paths:                                                                                                          READ PATH (instant): A judge clicks View Detail, hits FastAPI with Cognito auth, queries DynamoDB, returns rendered HTML.                                 WRITE PATH (async): An admin clicks Run Review, hits FastAPI with Cognito auth, creates a job in DynamoDB, enqueues to SQS, picked up by Lambda running a Strands Agent which fans out to 5 parallel judge agents, fans back in to a synthesis step, stores results back to DynamoDB. Seven layers top to bottom:    1. Presentation - Browser for Judge and Admin   2. Application - FastAPI with AWS Cognito                                                                                 3. Data - AWS DynamoDB                     4. Messaging - AWS SQS as the decoupling boundary between sync and async   5. Processing - AWS Lambda with Bedrock AgentCore and Strands Agent running 5 parallel judges that fan into synthesis   6. AI/LLM - AWS Bedrock using Claude Sonnet 4.5    7. External - GitHub API                                                                                                                                 Diagram requirements:   - Show both read and write paths clearly                                 - Show the fan-out and fan-in of the 5 judges   - Service names only, no table names, field names, or internal details   - Keep it minimal, one box per service, labels on arrows only where needed

Creator Notes(1)

This is an example of a representative architecture for the AI Hackathon application created by Vishu. The Hackathon application uses agentic patterns.

about 2 months ago

Community Discussion

Sign in to join the discussion

Sign in to comment

Be the first to comment

Share your thoughts on this architecture

AI Analysis(1)

AI Review
Tradeoff

about 2 months ago

I think the biggest production risk is putting a long-running, fan-out/fan-in AI orchestration inside a single Lambda behind SQS. That looks elegant on the diagram, but in practice you’re coupling queue retry semantics, Lambda timeout/concurrency limits, Bedrock latency, and GitHub API variability into one failure domain.

KB

Kevin Brown

@mathsociety

Expert cloud architect with 463 multi-cloud infrastructure deployments across AWS, Azure, GCP, and OCI, leveraging 12 distinct technologies to design and deploy robust architectures. Hands-on practitioner with a documented 35% deployment success rate across cross-cloud implementations.

View portfolio
Try it in the Playground

Open an interactive version ��� fork it, generate AI variants, or share it with your team.

What You'll Get

Editable diagram in your workspace
Interactive cost estimates
AI-powered customization
Save and share your version

Start Customizing

Make this template your own

Takes 30 seconds • No credit card required

Share

Statistics

Views
56
Clones
0
Likes
0

Details

Category
serverless

Estimated monthly cost

$12.64/month

Published
3/21/2026

Services Used

10 cloud services in this architecture

APIGateway
Lambda
DynamoDB
SQS
Cognito
Bedrock
SecretsManager
Agent-strands-orchestrator
Agent-judge
Agent-synthesis

Ready to build this?

Clone this architecture into your workspace and deploy it to your cloud account.

Takes 30 seconds • No credit card required

You Might Also Like

Cloud Architecture for Ad Network with Authentication
382

Cloud Architecture for Ad Network with Authentication

Please create a cloud architecture for an ad network. Features that we need include: user authentication on our…

AWS
AZURE
Serverless E-Commerce Platform with Real-Time Inventory
217

Serverless E-Commerce Platform with Real-Time Inventory

Design a serverless e-commerce platform with real-time inventory management. Use AWS Lambda for order processing,…

AWS
Global E-Commerce Platform with Multi-Cloud Failover
187

Global E-Commerce Platform with Multi-Cloud Failover

Create a global e-commerce platform with multi-cloud redundancy. Use AWS in us-east-1 for the primary application with…

AWS
AZURE
GCP
Scalable 3-Tier Web Application
152

Scalable 3-Tier Web Application

Create a basic web application on AWS with EC2 instances behind an Application Load Balancer, using RDS for the…

AWS