Smeron
AI infrastructure

DeployWhisper AI

An infrastructure-as-code orchestrator that translates natural language into scalable cloud deployments on AWS and GCP.

  • NLP
  • Cloud deployment
  • IaC
  • DeployWhisper AI — screen 1
  • DeployWhisper AI — screen 2
  • DeployWhisper AI — screen 3

Technologies used

  • Next.js
  • TypeScript
  • Node.js
  • Python
  • Terraform
  • AWS SDK
  • Azure OpenAI

Overall project details

DeployWhisper is an AI-powered infrastructure orchestration platform designed to simplify cloud deployments through natural language commands. By translating high-level user intent into production-ready IaC (Infrastructure as Code) templates, it bridges the gap between complex cloud architectures and rapid development. The system automates the provisioning of AWS/GCP resources and GitHub Actions, ensuring a seamless "Chat-to-Cloud" experience.

Target audience

  • Startup Founders & CTOs

    Needing to provision secure, scalable infrastructure without dedicated DevOps teams.

  • Frontend Developers

    Looking to deploy full-stack environments through simple conversational interfaces.

  • DevOps Engineers

    Seeking a rapid prototyping tool for standard cloud architectural patterns.

User experience & workflow

The platform is designed around a "Conversation-to-Provision" model, where the AI acts as a senior DevOps engineer guiding the user through architectural choices.

Technical architecture

The architecture relies on a specialized AI Inference Engine that translates natural language into structured Terraform modules, managed by a Node.js orchestration layer.

Developer role & focus

  • AI Intent Translation

    Developing the prompt engineering and vector-based logic to accurately map vague text to strict Terraform schemas.

  • Real-time Streaming Logs

    Implementing a WebSocket-based logging system to stream deployment progress from the runner directly to the user's dashboard.

  • Secure Credential Management

    Engineering a highly secure "Vault" system for managing cloud provider IAM keys and GitHub tokens.

  • State Management

    Leveraging React Query to handle the complex, long-running states of cloud deployments.

Technology stack

Core stack

Frontend
Next.js, TypeScript, Tailwind CSS, Monaco Editor
Backend
Node.js (API), Python (NLP/Inference), Socket.io

Infra Tooling

AI Engine
Azure OpenAI (GPT-4o), Pinecone Vector DB

Communication structure

The platform ensures a responsive experience by combining traditional RESTful patterns for configuration with WebSockets for real-time deployment logging.

Next projectAire Real Estate
Read case study