The New Stack
·
2 days ago
Port, an agentic software development company, launched its Port AI Builder service to address concerns about ungoverned AI-assisted coding by adding governance controls, human review, and organizational context to code generation. The platform uses a Plan Mode that drafts code, asks clarifying questions, and requires human approval before building, with all plans versioned and audited for traceability. The service aims to shift software quality assurance from manual processes to AI validation combined with human oversight, enabling teams to build production-grade code without accumulating technical debt from rushed development.
The New Stack
·
2 days ago
Model Context Protocol (MCP) faces criticism from developers for adding unnecessary complexity in small projects, but the skeptics overlook that enterprise agentic systems require MCP's capabilities for credential delegation, audit trails, and structural least privilege that direct API calls cannot provide. MCP enables security teams to embed authorization context at the tool-call level and structurally prevent agents from exceeding their assigned scope, whereas allowlists alone are insufficient governance in regulated environments. Enterprise adoption of agentic systems will require solving two remaining challenges: making capability-scoped server provisioning accessible to non-specialists and providing operational visibility tools for security teams to manage MCP connections across their environment.
Wired AI
·
2 days ago
The Department of Government Efficiency used AI tools at HUD to inform policy decisions including identifying regulations for rescission, but the agency is withholding over 100 documents about this work through FOIA denials. HUD cited nonexistent "AI privilege" and presidential communications privilege to exempt documents including files labeled "GPT defined Econ Analysis approach" and various regulatory analysis prompts created by DOGE team members. The lack of transparency about AI's role in government policymaking raises concerns about algorithmic bias and error, with no current U.S. law requiring disclosure of AI use in rule creation.
