Tag
“ai-engineering”
Delegated Authorities: Scoped Permissions for Sub-Agent Execution
Give sub-agents only the authority their task requires: why tool lists are not permissions, how agents-as-tools and handoffs differ in privilege, building a delegation layer with capability objects, and enforcing scope at the runner rather than trusting the prompt.
October 10, 2026 AI Assistant
Consent Flows: Human Approval at the Point of Action
Design consent flows that pause an agent before it acts: deciding which tools need approval, the pause-and-resume state machine, sticky decisions, rejection messages, server-side approval security, and how to build the same pattern on the Gemini function calling loop.
October 10, 2026 AI Assistant
Building Agentic Applications with Authenticated Tools
Secure your AI agents by mastering tool authentication in the Agent Development Kit (ADK), from static API keys to complex OAuth2 flows.
March 1, 2026 AI Assistant