
From Prompt to Verified DevOps Automation
AGX uses AI to generate structured JSON plans which are then statically validated against a pre-vetted function library before being compiled into production-ready code.
Describe what you want to automate...
Output
The Engine and The Roadmap
About the Showcase Engine
AGX is a verifiable AI engine that translates your commands into reliable, production-ready workflows.
This live showcase demonstrates our core principle: From Prompt to Verified Plan. We are actively expanding the function registry to cover more clouds and services.
- 🛡️ Reliable by Design. No Hallucinations.
Our verification engine validates every execution plan against a registry of approved functions before it runs, eliminating the random failures and unpredictable behaviour of typical AI agents.
- 👀 Transparent & Auditable
AGX generates a clean Python script for every task. You see exactly what will happen, providing a clear and auditable workflow every time.
- ⚙️ Built for Complex, Real-World Tasks
With built-in dependency resolution, the engine can orchestrate multi-step processes like building an image, deploying it, and then monitoring the result.
Available Tools:
check_docker_status
: Checks if Docker is running.build_docker_image
: Builds a Docker image.create_dockerfile
: Generates a Dockerfile.deploy_to_fly
: Deploys an application to Fly.io.scale_fly_app
: Scales a Fly.io application.get_app_status
: Gets the status of a Fly.io app.monitor_deployment
: Monitors a Fly.io deployment.cleanup_resources
: Cleans up Fly.io and Docker resources.
Try chaining them together in your prompt! Here's a sample: Create a Dockerfile for a Python FastAPI application on port 8000, build the image, and then deploy it to Fly.io.
The Future: The AGX CLI
The next evolution of AGX is a powerful, context-aware CLI designed for professional DevOps workflows. It will bring the same verifiable engine to your local machine, with state management, file system access, and deep integrations with AWS, Kubernetes, and more.
Coming Features:
- Local State Management
Track deployments, resources, and configurations across your entire infrastructure.
- AWS Integration
Deploy to EC2, Lambda, ECS, and manage RDS databases with natural language commands.
- Kubernetes Orchestration
Generate and apply manifests, manage deployments, and scale workloads safely.
- GitHub Actions Integration
Generate CI/CD pipelines that integrate seamlessly with your verification engine.
Interested in the CLI? I'm developing it with feedback from real-world DevOps teams. Reach out to discuss your use case and get priority access to the beta.
Five plans a day for now.