#security
security

Reviewing Agent-Written .NET Code: Green Builds Can Still Hide Bugs

Mehdi Mohseni argues that coding agents now write much of the code, but developers still need the judgment to spot code that looks right and is wrong. Using ASP.NET Core examples, he shows how generated code can compile, pass tests and still hide a fail-open security check or a silent misconfiguration. A practical read for anyone reviewing agent output.

Microsoft Agent Framework: Human-in-the-Loop Tool Approval with .NET

Agent Framework can pause an agent before a sensitive tool runs, using ApprovalRequiredAIFunction, until a person approves. The author shows the approval loop in a console app and over the Responses protocol on Microsoft Foundry. On Foundry, an approved booking still ends in a failed run, a caveat every hosted approval flow should account for.