According to Sundar Pichai on X, Google AI Studio now offers a full-stack vibe coding experience that combines the Antigravity coding agent with built-in Firebase integration to convert natural language prompts into production-ready apps. As reported by Sundar Pichai, this update streamlines app scaffolding, backend setup, and deployment by pairing an AI coding agent with Google’s managed backend services, reducing time-to-market for prototypes and MVPs. According to the post, developers can leverage prompt-based code generation, authentication, databases, and hosting in a single workflow, indicating a tighter coupling between AI-assisted development and serverless infrastructure that could lower DevOps overhead for startups and enterprise teams.

According to Nagli on Twitter, a public Firestore endpoint for project rentahuman-prod exposed full user records via a direct GET request to firestore.googleapis.com/v1/projects/rentahuman-prod/databases/(default)/documents/humans?pageSize=300. As reported by the tweet, the Firebase config was embedded in homepage JavaScript, enabling unauthenticated access. According to Google Firebase documentation cited by industry reports, improperly configured Firestore rules can allow read access to collections without auth, creating high-severity data exposure risks for AI-driven apps that store user data alongside model interaction logs. For AI product teams, the immediate business impact includes regulatory exposure, reputational damage, and model retraining data leakage; remediation should include tightening Firestore security rules to require auth, rotating API keys, auditing access logs, and implementing backend proxies for model and user data, as recommended by Firebase security guidance and standard OWASP API best practices.