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
A high-precision predictive system leveraging ensemble machine learning (XGBoost/LightGBM/CatBoost) to automate credit risk assessment and optimize financial lending decisions.
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
Framer skills are fun and useful.
Check out how I create a new page + CMS for this website.
You'll get 5 skills with the template from @Framer Marketplace https://www.framer.com/marketplace/templates/oda/
Bundling the skills with the template is a smart move, feels like you're selling the workflow and not just the layout. Does the agent keep the page consistent with the existing CMS styles on its own, or do you still end up nudging spacing by hand?
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.
At Procys, I design the exception path alongside document extraction.
Invoices and identity documents arrive in different layouts. OCR and LLM reasoning produce candidate fields. Deterministic checks validate headers, line items, and tax values. When confidence or record comparisons leave a field uncertain, the workflow sends it to a reviewer with the source context.
A good document AI system should make uncertainty visible before data moves into business systems.
If your team processes invoices or identity documents, which exceptions still take the most manual time?
edge cases are where doc AI earns trust, love that you design for them 👌
