Engineering · Ujex
Ujex trust engineering
Deep dives into agent passports, scoped mandates, approval gates, signed evidence, and production integration.
Scoped credentials for AI agents: separating identity from authority
Why a valid agent identity is only the start, and how expiring mandates constrain action, resource, budget, and consent.Read article →Benchmarking an agent trust layer: denial latency, replay safety, and evidence cost
A reproducible benchmark plan for the controls that sit between an agent request and a real side effect.Read article →Integrating the Ujex MCP server in production
From local emulators to agent enrolment, mandate checks, approval-gated tools, signed callbacks, and offline evidence verification.Read article →