The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
This project provisions AWS infrastructure using Terraform and automates the deployment process with GitHub Actions. The workflow creates a temporary self-hosted runner, runs Terraform on that runner, and then removes the runner along with the temporary network resources used for the job.
The repository combines infrastructure automation with a secure OpenVPN deployment on EC2, giving teams a reusable pattern for AWS deployment and remote access management.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
I haven’t posted much lately because the work got intense.
Two Webflow builds I’ve just finished: MavBio and Jemba9.
One works with biomaterials for medical and research applications. The other builds mission-critical technology for the space industry.
Very different worlds, and genuinely exciting projects to work on.
I’ve also wrapped up a much larger wellness platform that is now being turned into a full case study, while a few new projects are already underway.
A small preview for now. More soon!
wow, the smoothness is mindblowing here
This project focused on building and testing a practical AI security assessment lab for evaluating LLM defenses against prompt injection and jailbreak attacks.
I integrated Spikee by Reversec with a locally hosted cybersecurity model running through LM Studio, then added NVIDIA NeMo Guardrails to compare model behavior under three conditions: no guardrails, input filtering, and combined input/output protection.
The work included configuring the local model environment, building a custom FastAPI gateway, integrating NeMo Guardrails, troubleshooting model latency and timeout issues, creating a reusable Spikee target, and analyzing attack results using Spikee’s built-in reporting tools.
The project also explored different adversarial testing approaches, including prompt injection datasets, obfuscation, encoded attacks, Best-of-N testing, synthetic canary leakage tests, and structured benchmark comparisons.
The objective was to measure how much the guardrails reduced successful attacks while keeping the model, dataset, and testing conditions consistent.
Tools used: Spikee, NVIDIA NeMo Guardrails, LM Studio, Python, FastAPI, PowerShell, Parrot OS, local LLMs, JSONL datasets, and custom security testing scripts.
This project demonstrates a hands-on approach to LLM red teaming, AI safety testing, prompt-injection assessment, and guardrail validation for organizations deploying generative AI systems.
pretty cool tbh. testing the same attacks with different guardrail setups makes the results way more interesting.
Knowledge AI Logistics – Intelligent Fleet Management Platform I developed the concept and operational structure for an AI-powered fleet and logistics management platform designed to give transport businesses better visibility and control over their operations.
Giving transport teams real time insight into routes removes a lot of guesswork. The operational structure you outlined looks ready to turn data into actionable moves.