Skip to content

LevelUpBM/AIintakeform

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

LevelUp AI Intake — Deployment Guide

A conversational AI intake tool that walks clients through articulating their business problem, then generates a structured Problem Statement Brief for the LevelUp Applied Technology team.

What It Does

  • Client clicks a link → branded LevelUp chat experience
  • AI consultant guides them through the problem (People → Process → Technology)
  • After ~10 minutes, generates a structured brief with observations
  • Client can copy the brief or email it directly to justin@lvlup.au
  • Your API key stays server-side (never exposed to the client)

Deploy to Vercel (Recommended — 15 minutes)

Prerequisites

Step 1: Push to GitHub

# If you haven't already, install Git
# Then from this folder:
cd levelup-intake
git init
git add .
git commit -m "LevelUp AI Intake v1"
git branch -M main

# Create a new repo on GitHub called "levelup-intake" (don't add README)
# Then push:
git remote add origin https://github.com/YOUR-USERNAME/levelup-intake.git
git push -u origin main

Step 2: Deploy on Vercel

  1. Go to vercel.com/new
  2. Click "Import Git Repository"
  3. Select your levelup-intake repo
  4. Before deploying, click "Environment Variables"
  5. Add:
    • Key: ANTHROPIC_API_KEY
    • Value: Your Anthropic API key (starts with sk-ant-...)
  6. Click Deploy
  7. Wait ~60 seconds. Done.

Your app is now live at: https://levelup-intake.vercel.app (or similar)

Step 3: Send to Client

Email your client the link. That's it.


Add a Custom Domain (Optional — 5 minutes)

  1. In Vercel dashboard → your project → SettingsDomains
  2. Add: intake.lvlup.au (or whatever subdomain you want)
  3. Vercel gives you DNS records to add
  4. Add those records in your domain registrar (where lvlup.au is managed)
  5. Wait for DNS propagation (~5 min to 1 hour)
  6. Now clients visit: https://intake.lvlup.au

Run Locally (for testing)

cd levelup-intake
npm install
cp .env.example .env.local
# Edit .env.local and add your Anthropic API key
npm run dev
# Open http://localhost:3000

Project Structure

levelup-intake/
├── app/
│   ├── api/
│   │   └── chat/
│   │       └── route.js      ← Server-side API (keeps your key secure)
│   ├── layout.js              ← HTML wrapper, metadata, fonts
│   └── page.js                ← The full chat UI
├── public/                    ← Static assets (add logo here)
├── .env.example               ← Template for environment variables
├── .gitignore
├── next.config.js
├── package.json
└── README.md

Customisation

Change the AI's behaviour

Edit the SYSTEM_PROMPT in app/api/chat/route.js. This controls:

  • Conversation flow and question sequence
  • Tone and language style
  • Brief output format
  • How many exchanges before offering to generate the brief

Change the branding

Edit the colour constants at the top of app/page.js:

const NAVY = "#242B5A";   // LevelUp primary dark
const TEAL = "#007DAD";   // LevelUp primary accent
const GREEN = "#ADCE6D";  // LevelUp secondary accent

Add a logo

Drop your logo file into public/ and reference it in the header section of app/page.js.

Change the email recipient

Search for justin@lvlup.au in app/page.js and replace if needed.


Cost

Item Cost
Vercel hosting Free (hobby tier)
Custom domain Free (if you already own it)
Anthropic API per conversation ~$0.08–0.15 AUD
10 clients/month ~$1–1.50 AUD
50 clients/month ~$5–7.50 AUD

Security Notes

  • API key is stored as a Vercel environment variable (server-side only)
  • Client never sees the API key
  • Conversations are not stored — they exist only in the browser session
  • No cookies, no tracking, no analytics (add if you want)
  • Add rate limiting if you make the URL public (Vercel has built-in options)

Future Enhancements

When you've validated the concept with a few clients:

  • Auto-email the brief to you when generated (add SendGrid/Resend)
  • Save briefs to Azure SQL or SharePoint (integrate with existing infra)
  • Add analytics (how many started, how many completed)
  • Move to Azure App Service alongside Frank infrastructure
  • Create intake variants for different service lines (HR, Tech, Strategy)

Built by LevelUp Applied Technology · lvlup.au · Perth, WA

About

LevelUp AI Intake Form

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors