Live in productionNYU Cloud Computing · Spring 2026

Summarize, question, and visualize any research paper.

A serverless AWS platform that searches arXiv and Semantic Scholar, fetches full-text PDFs, and produces structured summaries plus a retrieval-augmented chat and an interactive knowledge graph — all in about thirty seconds per paper.

Paper → summary
~30s
Lambdas, 7 stacks
13
Per summary
$0.20
Idle cost
0

Product

What you can do once you sign in

Everything below is live in production today. Sign up, paste a topic, and get back a structured summary, an interactive chat, and a knowledge graph in under a minute.

Search

Search across two sources

arXiv and Semantic Scholar queried in parallel, deduped by arxivId / DOI / normalized title. Phrase-quoted title boost so an exact title returns the right paper.

Summarize

Structured summaries

A five-section structured summary — Objectives, Methodology, Results, Limitations, Contributions — plus auto-extracted keywords, generated end-to-end in about thirty seconds.

RAG chat

Talk to the paper

Ask any question about a paper. Each answer is grounded in retrieved chunks with inline citation tooltips showing chunk number, similarity score, and excerpt.

Visualize

Knowledge graph

Auto-extracted entities (methods, datasets, metrics, results) and relationships rendered as an interactive graph with a key-concepts rail and click-through neighbours.

Discover

Library similarity

Mean paper-level embeddings let us surface the three most similar papers from your own library, side-by-side with the one you are reading.

Export

One-click export

Copy any summary as Markdown, download as .md, or grab a clean BibTeX entry with the canonical lastnameYear key.

Architecture

Serverless on AWS, end to end

Every service is managed — no virtual machines, no containers to babysit, no idle compute charges. The async pipeline is orchestrated by Step Functions; LLM and embedding calls go through Amazon Bedrock.

AWS architecture diagram showing edge, API, pipeline, and data layers

Figure 1 — AWS deployment topology

Services

Every piece earns its place

Nine functional areas spanning thirteen Lambdas and seven CDK stacks. Hover for the role each one plays.

Edge

Route 53 + CloudFront

DNS, HTTPS on a custom domain, and global edge caching sit in front of the static frontend. A CloudFront Function rewrites nested SPA routes server-side.

Auth

Amazon Cognito

Managed user pool with email verification, SRP login, and forgot-password flow. API Gateway validates JWTs before any Lambda runs.

API

API Gateway + 13 Lambdas

REST entrypoint with eight authenticated endpoints — health, search, summarize, list/get summaries, related, graph, chat, quota.

Orchestration

SQS + Step Functions

Async pipeline: SQS decouples the API from long work; Step Functions coordinates five Lambdas with retries, parallel map, and a failure handler that flips DynamoDB.

LLM + embeddings

Amazon Bedrock

Qwen 3 Next 80B (Claude Sonnet swap-ready) for summarization, chat, and graph extraction. Titan Text Embeddings v2 for chunk vectors.

Data

DynamoDB + S3

DynamoDB single-table for users, jobs, summaries, embeddings, and graphs with one GSI for cross-user dedup. Two S3 buckets — frontend and raw PDFs with lifecycle policy.

Observability

CloudWatch + X-Ray

Structured JSON logs, four alarms wired to SNS email, X-Ray traces across every Lambda and Step Function execution, an operations dashboard, and an AWS Budgets alarm.

Infrastructure as Code

AWS CDK

Seven reproducible TypeScript stacks — Auth, Data, Pipeline, Api, Frontend, Ops — deployable from scratch with one command.

CI

GitHub Actions

Lint and build on every pull request. The whole infra is checked with cdk synth before merge.

Production numbers

Verified, not aspirational

Every number below comes from real executions on the live deployment.

End-to-end summary
27–44s

real arXiv papers

Search P95 latency
~1.4s

arXiv + Semantic Scholar in parallel

Cost per summary
$0.20

Bedrock-dominated

Idle infrastructure
$0

serverless, pay-per-use

Tests passing
14 / 14

vitest

API 5xx errors
0

lifetime

Knowledge graph
~25s

first call, instant after

Free tier coverage
100%

excluding Bedrock

Team

Four engineers, one repo

One owner per architectural area. Everyone reviews everyone else's pull requests.

SS

Shreyas Sankpal

Pipeline & Orchestration

PM

Pranjal Mishra

Architecture & Frontend

YZ

Yang Zheng

Search & Data Layer

KH

Kerry Huang

Auth & API