Writer adds company-controlled text watermarking and agent governance

Summary

Writer released new features giving enterprises control over AI text watermarking, agent workflows, security, and data protection. The platform now supports company-specific watermarks tied to private keys with adjustable strength. It also added human-in-the-loop playbook approvals, administrative controls, a security scanner for skills, data loss prevention guardrails, and real-time agent redirection.

What changed

• Added text watermarking tied to private keys with adjustable strength for Palmyra models.
• Introduced playbook approvals for structured human reviews in agentic workflows.
• Shipped a skill security scanner that reviews imported skills for hidden risks.
• Added real-time agent redirection so users can adjust tasks and queue follow-up requests while agents work.

Availability

“This month, we’re releasing a set of features that give enterprises more control over how they identify, trace, and govern their work — starting with our approach to text watermarking and extending across interoperability, workflow governance, collaboration, and security.”

Source