Agents Prompt Library - Mint Starter Kit

The Problem

At Awaaz.AI, our voice agents are powered by carefully crafted prompts — system instructions that define how an agent behaves on a call. Today, these prompts live in Google Docs and Drive folders. This creates real problems:

No version history you can actually use — Google Docs tracks character-level edits, not meaningful prompt versions. Rolling back to “the version that worked well last Tuesday” is a nightmare.
No structure — Prompts have variables like {{user_name}}, {{language}}, {{loan_amount}} but there’s no way to test them with real values without copy-pasting into a playground.

You’re going to fix this.

Your Mission

Build a Prompt Library — a full-stack web app where the team can:

Create and organize prompt templates with metadata
Fill in variables and preview the rendered prompt
Test prompts against an LLM and see the response instantly
Track versions so we know what changed and when

Time Budget

You have 4 hours.

Technical Requirements

Database Layer (PostgreSQL)

Design a schema that stores:

prompts
├── id (uuid)
├── name (e.g., "Loan Reminder Agent — Hindi")
├── description
├── category (e.g., "collections", "onboarding", "survey", "verification")
├── language (e.g., "hi", "en", "es", "mr")
├── template_body (the prompt text with {{variables}})
├── variables (JSON array of variable definitions)
├── version (integer, auto-incrementing per prompt)
├── is_active (boolean)
├── created_at
└── updated_at

prompt_versions
├── id (uuid)
├── prompt_id (foreign key)
├── version (integer)
├── template_body (snapshot of the prompt at this version)
├── change_note (e.g., "Made tone more polite for rural users")
├── created_by
└── created_at

Backend Layer

Build the following API endpoints: CRUD

GET /prompts — List all prompts (with filters: category, language, search by name)
GET /prompts/:id — Get a single prompt with its version history
POST /prompts — Create a new prompt
PUT /prompts/:id — Update a prompt (auto-creates a new version)
DELETE /prompts/:id — Soft delete (set is_active = false)

Render & Test

POST /prompts/:id/render — Accept variable values, return the rendered prompt with all {{variables}} filled in
POST /prompts/:id/test — Render the prompt, send it to an LLM API, return the model’s response

Versions

GET /prompts/:id/versions — List all versions of a prompt
GET /prompts/:id/versions/:version — Get a specific version
POST /prompts/:id/rollback/:version — Rollback to a previous version (creates a new version with the old body)

Frontend Layer (React or HTML + JS)

Build a single-page app with these views: Prompt List Page

Searchable, filterable table/grid of all prompts
Show name, category, language, version number, last updated
Filter by category and language

Prompt Editor Page

Text editor for the prompt template body
Auto-detect {{variables}} from the template and show input fields for each
Live preview panel showing the rendered prompt as you type variable values
“Save” button that creates a new version with an optional change note

Test Panel

Fill in variables → click “Test with LLM” → see the model’s response
Show latency and token count of the LLM response

Version History

List of past versions with timestamps and change notes
Click to view any version
“Rollback to this version” button

Example Prompt Template

Here’s what a prompt in the library might look like: Name: Loan Reminder — Hindi Category: Collections Language: hi Template:

You are a polite loan reminder agent for {{company_name}}.
You are calling {{user_name}} regarding their pending EMI payment.

Details:
- Loan ID: {{loan_id}}
- EMI Amount: ₹{{emi_amount}}
- Due Date: {{due_date}}
- Days Overdue: {{days_overdue}}

Instructions:
- Speak in Hindi (Hinglish is okay)
- Be polite but firm
- If the user says they will pay, ask for a specific date
- If the user says they cannot pay, ask about their situation empathetically
- Never threaten or use aggressive language

Variables:

[
  {"name": "company_name", "type": "string", "default": "Awaaz Financial"},
  {"name": "user_name", "type": "string"},
  {"name": "loan_id", "type": "string"},
  {"name": "emi_amount", "type": "number"},
  {"name": "due_date", "type": "date"},
  {"name": "days_overdue", "type": "number"}
]

Constraints & Ground Rules

Constraint	Requirement
Backend	Python + FastAPI/Django
Database	PostgreSQL
Frontend	React or Angular
LLM API	Use OpenAI or Gemini API for the test feature (API key will be provided)
Auth	Skip authentication
Deployment	Run locally. No need to deploy.

Evaluation Criteria

Criteria	Weight	What We’re Looking For
Working CRUD	25%	Can you create, read, update, and list prompts end-to-end?
Variable Rendering	20%	Does the template engine correctly fill in `{{variables}}`? Live preview works?
LLM Test Feature	20%	Can you render a prompt and get an LLM response from the UI?
Version History	15%	Are versions tracked? Can you view and rollback?
UI/UX	10%	Is the interface clean and usable? (Doesn’t need to be pretty — needs to be functional)
Code Quality	10%	Clean structure, error handling, separation of concerns

Bonus Challenges 🏆

Diff View: Show a side-by-side diff between two prompt versions (use a library like diff-match-patch or jsdiff)
Prompt Duplication: “Clone this prompt” button to quickly create a variant (e.g., same prompt but for a different language)
Tag System: Add freeform tags to prompts for more flexible organization
Response Rating: After testing with an LLM, let the user rate the response (👍/👎) and store it — helps track which prompt versions perform best
Export: Export a prompt as JSON or Markdown for sharing

🏆 Hackathon Prize

The winner receives a USD $20 one-time credit towards a course or book of their choice.

​The Problem

​Your Mission

​Time Budget

​Technical Requirements

​Database Layer (PostgreSQL)

​Backend Layer

​Frontend Layer (React or HTML + JS)

​Example Prompt Template

​Constraints & Ground Rules

​Evaluation Criteria

​Bonus Challenges 🏆