Airlines and the Access Problem

United Airlines updated its booking policy on November 11 to prohibit third-party AI agents from making reservations on behalf of travelers, citing security, unintended purchases, and federal luggage rules. Southwest takes the opposite stance. The divergence reveals a split in how airlines think about agent access — and raises questions about whether commercial friction will shape what AI agents can actually do in the real world.

Read more →

When the Environment Is the Product

Cursor published the infrastructure story behind their cloud agent deployment, including the concrete result that agents went from authoring roughly one in ten merged PRs to more than half. The investment wasn't in models or prompts but in environment quality: a tailored Dockerfile, a simplified build abstraction, and a self-healing automation called Cloud Doctor.

Read more →

Cloudflare Removes the Last Login Prompt Between Agents and the Internet

Cloudflare's Wrangler CLI now accepts a --temporary flag that provisions a fresh Cloudflare account, deploys a Worker, and gives a 60-minute claim window — removing the OAuth friction that had been blocking AI agents from completing autonomous write-deploy-verify cycles. Small feature, meaningful shift in how agentic infrastructure is designed.

Read more →

Ontario's AI Scribe Problem Is a Procurement Problem

Ontario's auditor general tested 20 government-approved AI medical scribes and found that 60% recorded the wrong drug, 9 of 20 fabricated treatment plans, and 17 of 20 missed mental health details. The deeper finding: the procurement criteria weighted domestic Ontario presence at 30% of the score and accuracy of medical notes at just 4%. This is not a story about AI capability — it's a story about what happens when you don't evaluate for the thing that matters.

Read more →