Search indexed enterprise systems and answer only from the connected knowledge available to the user.
The Connected Knowledge Search Agent Skill helps an agent retrieve and synthesize information from indexed enterprise systems such as Jira, Confluence, GitHub, Drive, email, calendars, and meeting sources. Answers stay grounded in available connected content, and the underlying connectors and access controls determine what can be retrieved.
Product behaviour reviewed against VDF AI Cloud · 2026-09-04Match the Skill to the job, provide the required context, and decide what a useful output must contain before the agent begins.
The Skill supplies structured judgement and sequencing. VDF AI supplies the separately governed capabilities used during each step.
Identify which connected systems and time range are likely to contain the requested information.
Confirm that relevant source collections are indexed before treating a missing result as evidence.
Search permitted collections and preserve source identity as material is brought into context.
Synthesize only what the indexed evidence supports and state when the available corpus is incomplete.
Connected Knowledge Search can call these capabilities only when they are assigned to the agent and authorised for the user. The Skill itself never expands access.
“Find our latest decisions, tickets, and meeting context for the identity migration and summarize the open work.”
A source-grounded project brief with links to indexed records and a visible list of missing coverage.
Connected Knowledge Search gives the agent a repeatable method. Tool permissions stay separate, and the capability can run inside a governed multi-agent Network.
Use these relationships as starting points, then narrow the agent’s access and workflow to the actual business context.
A reliable Agent Skill states its boundaries as clearly as its capabilities, especially when the workflow can influence decisions or external systems.
It can search the systems that your VDF AI environment has connected and indexed, including supported work-management, code, document, email, calendar, and meeting sources.
No. Retrieval remains bounded by configured connectors, indexed collections, and the user and agent permissions enforced by the platform.
The result should report the coverage gap instead of pretending the requested information was not found anywhere in the organisation.
Assign the Skill, grant only the tools the agent needs, and test the workflow with your own controlled context.