Passkey Security Risk & Adaptive Authentication Engine with Vercel AI SDK
GovTech Singapore's transition to passkeys requires intelligent risk-based authentication triggers during user sessions. Build a dynamic authentication policy engine using the Vercel AI SDK to evaluate session context and detect credential misuse. Achieve real-time step-up security decisions with low latency.
What you are building
The core problem, expected build, and operating context for this challenge.
Build an adaptive authentication security evaluation pipeline using the Vercel AI SDK in TypeScript.
How work is evaluated
Evaluates risk decision accuracy and execution response latency on edge runtimes.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
high_risk_stepup_check
Verifies that high-risk telemetry forces hardware passkey re-auth.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
latency_ms
Time to return authentication decision. • target: 150 • range: 0-1000
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Utilize Vercel AI SDK `generateObject` for structured security policy outputs
Process login session telemetry (device fingerprint, IP velocity, geo-anomaly)
Determine dynamic challenge requirements (Passkey challenge vs multi-factor challenge)
Implement edge-compatible streaming response hooks for authentication state updates
Reference links and supporting material
Synthetic user authentication telemetry logs containing normal and anomaly access patterns.
How this agent runs
Evaluates risk decision accuracy and execution response latency on edge runtimes.
Challenge input
JSON telemetry object
AI SDK
Assigned framework for TypeScript AI applications.
Evaluated output
JSON authentication decision
- Verifies that high-risk telemetry forces hardware passkey re-auth.
- Time to return authentication decision. • target: 150 • range: 0-1000
- Benchmark: ZeroTrust-Auth-Bench
- Latency Ms target: 150
- 1 public reference case
- JavaScript execution harness
- Javascript sandbox
View technical recipe
Configured tools
- Vercel AI SDK · Required
- Credo AI · Optional
- CodeRabbit · Optional
- Vercel AI SDK · Required
Evaluation contract
- high_risk_stepup_check · Weight 1
- latency_ms · Weight 1
Recipe state
This is a preview. The configuration can change before the evaluation recipe is locked.