AI Assistant Mobile App — Backend API, AWS Lambda & DynamoDB
Overview
The backend for an AI assistant mobile app, running serverless on AWS Lambda with DynamoDB as the primary store. It covers the app's own surface — signup, signin and password reset, conversation history, and uploads for image, audio and video, including a live video socket — with S3 for file storage, SES for transactional email, and CloudFront and Route 53 in front.
Behind that sits the media understanding side. Uploaded audio runs through transcription models on EC2 to produce text, and uploaded video is analysed on EC2 to describe what happens in it scene by scene, keyed to the points where the scene changes. Both results are written back to DynamoDB and exposed over APIs to a separate team, who built the RAG layer on top of them — so this work supplied the searchable text the assistant reasons over, rather than the retrieval itself.
Outcome
A serverless backend powering an AI mobile assistant end to end — auth, conversations, uploads and live video — plus the EC2 pipeline that turns uploaded audio and video into searchable text and hands it to the RAG team over APIs.
Screens & Demos
Architecture & Pipeline
-
01
Mobile Client
AI assistant app
-
02
CloudFront + Route 53
Global edge
-
03
AWS Lambda
Custom Python router
- AWS
- Python
-
04
JWT Authentication
Per-user auth
-
05
Media Uploads
Image · audio · video · live socket
-
06
EC2 Transcription
Audio to text
-
07
EC2 Scene Analysis
Video described per scene change
-
08
DynamoDB · S3 · SES
Storage + email
-
09
APIs to RAG Team
Extracted text served on
End-to-end flow, in order. Scroll sideways on a narrow screen.
Key Features
- Full auth flow (signup, signin, forgot password) with JWT
- Conversation APIs with latest-conversation lookups
- Image, audio, and video upload endpoints
- Live video socket implementation
- Audio transcription models running on EC2, turning uploads into text
- Video scene analysis on EC2, describing what happens across scene changes
- Derived transcripts and scene descriptions stored in DynamoDB
- APIs serving that extracted text to the separate team building the RAG layer
- AWS S3 for file storage and SES for transactional email
- Custom Python routing layer on AWS Lambda
- Automated database maintenance scripts for DynamoDB
- CloudFront + Route 53 for global delivery