AI innovation continuously monitors changing source material and live support signals, identifies knowledge gaps and errors, and drafts precise updates to support knowledge

Stonly, the agentic AI and knowledge platform for customer service, announced the launch of Knowledge Agents, a new AI capability designed to help support organizations keep the knowledge used by customers, agents, and AI 100% accurate and up to date.

Knowledge Agents go beyond the basic generation and suggestion capabilities of current tools to address the harder problem: continuously monitoring source material and live support signals, identifying meaningful knowledge gaps, inconsistencies, and changes, and drafting precise updates to structured knowledge for easy human review and approval.

As companies try to scale AI in customer service, most are doing it on top of knowledge that changes constantly: policies, product updates, ticket-handling practices, compliance documents, and internal feedback. In most organizations, knowledge goes stale, gaps go undetected, and conflicts accumulate faster than teams can find and fix them. The result is a weak foundation for both human support and AI.

With Knowledge Agents, Stonly introduces AI agents that work 24/7 to build and manage the kind of operational knowledge customer service requires to operate reliably. As source material changes, Knowledge Agents identify where those changes matter across the knowledge base, determine what needs to be updated, draft the edits, and route them for approval. For knowledge teams that are almost always under-resourced relative to the volume of change they need to manage, this automates work that is almost entirely manual today.

“Knowledge teams always tell us they are ‘small but mighty.’ They do not have a content generation problem, they have a change-management problem,” said Alexis Fogel, Founder and CEO of Stonly. “Critical information changes constantly across dozens of places, with different owners, formats, and purposes. Knowledge Agents help teams keep their support knowledge current and accurate so both agents and AI can operate from what is actually true.”

Marketing Technology News: MarTech Interview with Miguel Lopes, CPO @ TrafficGuard

What Knowledge Agents Do

Monitor and Update

Teams connect their sources of truth: resolved tickets, search and AI queries, SharePoint, Confluence, Google Drive, websites, PDFs, and other systems that hold truth in the organization. Knowledge Agents continuously monitor those sources. When something changes, they trace the impact across support knowledge bases and help centers, identify every guide, workflow, and article where the change is material, and draft the update. Not summaries or generic rewrites, but precise edits: new branches, new steps, insertions, and replacements. Everything appears in a dashboard where teams can review, adjust, approve, and publish.

Knowledge Health Score

Separate from source changes, Knowledge Agents continuously audit content for broken links, conflicts, duplicates, and inconsistencies; the issues that confuse both people and AI. Teams get a configurable view of knowledge health that would otherwise require hours of manual auditing, along with detailed suggested fixes to strengthen the underlying source of truth for customer service.

Prompt-Based Knowledge Operations

Teams can ask questions and give multi-step instructions to simplify knowledge management work. Knowledge Agents can execute projects such as “Find every place we reference ‘refund rules’ and replace it with ‘returns policy,’ but only where it relates to in-store purchases,” across the entire knowledge base. From content creation to answering natural-language questions about the knowledge base, knowledge management tasks that normally take hours can be completed by Knowledge Agents in moments.

Marketing Technology News: Is the Traditional CDP Already Out of Date?

Why It Matters Now

When knowledge falls behind, the costs are tangible. Agents take longer to find answers, interrupt teammates, escalate issues that should not need escalation, and make mistakes because the right information was not there. Customers feel it in self-service, with missing or wrong information driving frustration, lower satisfaction, and more contact volume.

Now, AI has made the problem mission-critical. Customer service AI is designed to operate from the knowledge it is given, which is how organizations reduce hallucination risk. But unlike a human agent, AI cannot use judgment to detect that the underlying content is wrong. If the knowledge is inaccurate, incomplete, or inconsistent, AI scales that problem across every interaction. What was once painful is now impossible to ignore.

“At the same time that AI made accurate, structured knowledge essential,” Fogel explained, “agentic AI enabled Stonly to develop advanced Knowledge Agents that automate the most challenging parts of knowledge management that were not possible before.” The result is a foundation that keeps pace with the business, so every agent, every self-service experience, and every AI interaction operates from knowledge that teams can trust.