You will get an AI SaaS MVP in weeks: auth, billing, dashboard, and a real AI feature
Project details
You get a complete AI SaaS MVP in weeks: a deployable product with sign-up, paid plans, a working dashboard, and a real AI feature, not a clickable prototype. The stack is Next.js, TypeScript, and Node, with PostgreSQL, auth, and billing wired in, deployed to a host you control. The AI layer uses the Claude or OpenAI API, with retrieval (RAG) and function calling where the feature needs to act on your real data, not just chat.
Nine years full-stack, now focused on AI-native builds. The scope is named, not open-ended: we agree on one core loop before I start, so a fast timeline never means cut corners.
I built a live demo so you can judge the craft before we talk: sign in, land on a dashboard, ask a question about your metrics in plain English, and get a written answer plus the chart and the data source behind it, then manage plans on a real billing screen. It is a demo of what I build, a fictional product rather than client work.
You own everything at handoff: the full repository, deployment access, and all prompts. Tell me your one core feature and I will name the scope, timeline, and price precisely.
Nine years full-stack, now focused on AI-native builds. The scope is named, not open-ended: we agree on one core loop before I start, so a fast timeline never means cut corners.
I built a live demo so you can judge the craft before we talk: sign in, land on a dashboard, ask a question about your metrics in plain English, and get a written answer plus the chart and the data source behind it, then manage plans on a real billing screen. It is a demo of what I build, a fictional product rather than client work.
You own everything at handoff: the full repository, deployment access, and all prompts. Tell me your one core feature and I will name the scope, timeline, and price precisely.
AI Algorithms
Large Language Model, Transformer ModelAI Applications
Conversational AI, Natural Language Generation, Natural Language UnderstandingAI Models
ChatGPT, GPT-4What's included
| Service Tiers |
Starter
$4,000
|
Standard
$8,000
|
Advanced
$14,000
|
|---|---|---|---|
| Delivery Time | 14 days | 28 days | 42 days |
Number of Revisions | 2 | 3 | 3 |
AI Model Integration | - | - | |
Batch Normalization | - | - | - |
Database Integration | |||
Detailed Code Comments | |||
Image Upscaling | - | - | - |
MLOps | - | - | - |
Model Deployment | - | - | |
Model Documentation | - | - | |
Model Monitoring | - | - | - |
Model Testing & Optimization | - | - | |
Model Tuning | - | - | - |
Natural Language Processing | - | - | |
NLP Tokenization | - | - | - |
Pre-Training | - | - | - |
Prompt Engineering | - | - | |
Setup File | - | - | - |
Source Code |
Optional add-ons
You can add these on the next page.
Extra Core Feature
(+ 5 Days)
+$1,000
RAG Over Your Documents
(+ 7 Days)
+$3,000
Third-Party Integration
(+ 5 Days)
+$1,000Frequently asked questions
About Miguel
AI-Native Product Engineer - Chatbots, Agents & SaaS MVPs
Barcelona, Spain - 1:33 pm local time
Recent work shows what that looks like in production. I built an AI-powered education platform on Next.js and Expo using GPT-5 and Claude, including an SDK that was adopted across multiple institutions. I built a fintech digital wallet in React Native and Expo, backed by a NestJS and TypeScript microservices stack on AWS. And I ship my own AI products: a self-hosted AI pipeline workbench with its own MCP server, an agent-native engine that runs agents in a loop, a conversational booking app, and AI editorial and design tools.
What that means for you: I understand the full path from a model call to a deployed, reliable product. Auth, billing, retrieval, tool-calling, evaluation, and the unglamorous parts (logging, retries, guardrails) that decide whether an AI feature survives contact with real users.
How I like to work: tight scope, clear milestones, and a working demo early so you can steer before the budget is spent. I write clean, typed, tested code and I document what I hand over.
If you want a defined outcome at a fixed price, I package the most common builds (chatbots, RAG assistants, agents, SaaS MVPs, AI-commerce storefronts) as fixed-price projects below. Start there, or message me to scope a custom build.
Steps for completing your project
After purchasing the project, send requirements so Miguel can start the project.
Delivery time starts when Miguel receives requirements from you.
Miguel works on your project following the steps below.
Revisions may occur after the delivery date.
Kickoff and scope lock
We lock your one core feature, the stack, and access to your data, billing, and AI keys. I set up auth and the app shell and share a live preview link.
Build the core loop
I build your feature end to end on a clean, responsive dashboard, wiring billing, plans, and roles where your tier includes them. You steer on the live preview.