Scribd
Upload
12 views3 pages

Problem Statements - Build With AI

The document outlines two problem statements for building AI applications: a Composable AI Studio that allows users to create mini AI apps using modular intelligence blocks, and a Composable AI Mock Interviewer that adapts and evaluates interviews based on user input. Both solutions require specific features such as drag-and-drop functionality, adaptive questioning, and evaluation logic. A recommended tech stack is provided for both frontend and backend development, along with optional storage and UI tools.

Uploaded by

meerabaichadhana22
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
12 views3 pages

Problem Statements - Build With AI

The document outlines two problem statements for building AI applications: a Composable AI Studio that allows users to create mini AI apps using modular intelligence blocks, and a Composable AI Mock Interviewer that adapts and evaluates interviews based on user input. Both solutions require specific features such as drag-and-drop functionality, adaptive questioning, and evaluation logic. A recommended tech stack is provided for both frontend and backend development, along with optional storage and UI tools.

Uploaded by

meerabaichadhana22
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Build with AI - Problem Statements

Problem Statement 1: Composable AI Studio

Build a modular AI builder that lets users assemble “intelligence blocks” (like Lego) to create
mini AI apps without backend-heavy coding.​

❖​ Challenge :

Create a Composable AI Studio where users can visually combine:

●​ AI models
●​ Prompts
●​ Tools
●​ Memory
●​ Data source

…to build mini AI apps without writing backend-heavy code.​

❖​ Must-Have Requirements :​

●​ Flow builder - Drag-and-drop or node-based flow


●​ Minimum 3 blocks - At least 3 composable blocks (e.g. Prompt → Model → Output)
●​ Execution engine - Clicking “Run” executes blocks in sequence and produces output
●​ Ability to remix or reuse components
●​ Live preview or output panel

​
Problem Statement 2: : Composable AI Mock Interviewer

Build an AI interviewer that adapts, evaluates, and gives feedback using composable blocks —
not a static question list.​

❖​ Challenge :

Your product must allow a user to:

1.​ Select interview type (HR / Tech / Behavioral)


2.​ Provide context (resume text / role / skills) OR choose preset
3.​ Run an interview with at least 5 Q&A turns
4.​ Get scores + feedback
5.​ See final interview report​

Must-Have Requirements (Minimum Feature Set) :

●​ Composable interview flow - Role Block (interview type), Question Generator, Memory
(tracks answers), Evaluation block (scoring), Feedback block (improvement tips)
●​ Adaptive questioning - Next question must depend on: previous answer OR chosen
role/skill focus
●​ Evaluation logic + Audio mode
●​ Final report
●​ Working UI
●​ Candidate screen: Q&A experience + output panel
Recommended Tech Stack (24-Hour Friendly)

Frontend (Choose 1)

●​ [Link] + React + Tailwind + shadcn/ui


●​ Vite + React + Tailwind
●​ Vue + Tailwind

Backend (Choose 1)

●​ [Link] (Express)
●​ NestJS
●​ Serverless

AI Layer

●​ OpenAI / Gemini / Groq / Anthropic


●​ Use structured outputs

Storage (Optional but useful)

●​ Firebase
●​ MongoDB
●​ Supabase

Flow / Node UI (Optional)

●​ React Flow
●​ Or simple step builder​

Need Help ?

📧
For any queries or support, reach out to us at:​
support@[Link]

You might also like