Jev and CodeGraph for security review
The typesafe-security-review project combines Jev’s probability judgments with a code graph and OWASP/CWE data for low-cost security scanning.
A developer used TypeSafe's Jev to route agents and prune context, building ScamCheck—a scam detection API—in about an hour. Paste a message to get a scam score and red flags, at ~100ms and ~$0.00001 per check.
Everyone’s using Jev @typesafeai to route agents and prune context. A pretty useful use case is catching fake texts and other scams Built ScamCheck in about an hour, a scam detection API. Paste in a message and get a scam score + the red flags ~100ms/check ~$0.00001/check👇