Red Teaming Quickstart (No-Code)
Red Teaming Quickstart (No-Code)
Run your first risk assessment in the platform UI — no code required.
Red Teaming Quickstart (No-Code)
Run your first risk assessment in the platform UI — no code required.
This quickstart walks you through running your first no-code risk assessment on Confident AI. By the end of this guide, you’ll have:
No-code risk assessments let any team member analyze an AI application for security and compliance issues directly in the Confident AI platform.
Risk assessments follow a simple 4-step process:
Your AI app can be any application reachable over the internet — Confident AI communicates with it directly through your configured AI Connection.
Here’s a visual representation of the data flow during a risk assessment:
You’ll need a Confident AI account to follow along. Sign up here if you haven’t already.
First, set up an AI Connection so Confident AI can communicate with your app.
A framework defines the vulnerabilities and attacks that will be used in your assessment.
You can edit vulnerabilities, attacks, and priorities anytime from the framework configuration page.
From your framework configuration page, click Run Assessment and select the AI Connection you want to test.
Confident AI will generate adversarial inputs from your framework and send them to your app.
Name your assessments descriptively (e.g., “compliance-test-feb-11”) so they’re easy to find later.
Once the assessment completes, your report will be available in the risk profile section.
The report includes:
Done ✅. You’ve run your first no-code risk assessment. You can also download a PDF report with the full breakdown and remediation recommendations.
Now that you’ve run your first risk assessment, dive deeper into the platform: