Products
The Secuvon platform, and what runs today
Secuvon tests AI agents before they ship and is growing into the rest of the AI security lifecycle. Each product below says whether it runs in this release.
- LiveYou can use this in your workspace today.
- Partly livePart of this is in your workspace today; the rest is still being built.
- In progressWe are building this now. The workspace menu shows where it will appear, but it does not run yet.
- Live
Scanner
Assess a saved AI agent with a fixed, versioned test profile and review the graded evidence behind every finding.Learn more → - Live
Guardian
Inspect the messages an agent sends and receives in production, and block or redact what breaks your rules.Learn more → - Live
Red Teaming
An adversarial preset of chained tests that replay authored conversation prefixes against your agent.Learn more → - Live
Compliance
Map executed test evidence to framework references and bundle it for a reviewer, without claiming certification.Learn more → - Live
Discovery
Probe the HTTP endpoints you list, find the AI agents behind them and keep one inventory of models, tools and data.Learn more → - Live
Scheduling & Drift
Re-run assessments on a schedule and compare graded history to see when an agent's security moves.Learn more → - Live
Scan Comparison
Compare scored runs of the same agent and recorded model pass rates by module, down to the changed findings.Learn more → - Live
Teams & RBAC
Work in one workspace with your team, with roles, single sign-on and automatic provisioning.Learn more → - Live
Alerts
Send what Secuvon finds to your alert channels, ticketing and CI through signed webhooks.Learn more →
More in the workspace
The workspace menu also holds these pages, each with the same status.
- ActivityYour recorded account activity, with filters and audit-event details.Live
- AgentsThe agents you assess, each with its provider, model, saved credential and latest result.Live
- Prompt versionsCreate, compare and activate saved prompt revisions in your own workspace.Live
- Vendor riskA register of declared suppliers and self-reported questionnaire assessments.Live
- Model toolsRecord declared tool scopes and use model documentation and planning utilities.Live
- PoliciesPolicy-as-code rule sets evaluated against your scored scans, with a deploy gate for your pipeline.Live
- BenchmarkYour agents' scored security posture and its daily history, from your own scans.Live
Start with an assessment
The scanner runs today. Read how it grades before you trust a result.