Find internal experts with Claude
Turn Claude into an expert finder that runs an expertise search across team chat, knowledge base pages, tickets, and documents, confirms each person's team and role, and returns ranked experts with evidence for faster expert discovery.
Copied
When a user asks Claude to find an expert on a topic, it calls the scenario with an on-demand trigger via the Make MCP connection and provides 'topic' as a scenario input. The scenario triggers an AI agent running on [AI model provider]. The agent decides which searches to run across [team chat platform, e.g. Slack, Microsoft Teams], [knowledge base/wiki, e.g. Confluence, Notion], [issue tracker, e.g. Jira, Linear], and document authorship in [document storage platform, e.g. Google Drive, SharePoint], refining its queries based on what it finds. It then cross references the people it surfaces against [HRIS, e.g. BambooHR, Workday, HiBob] to confirm their team and role, ranks the most likely experts, and generates a response with each person's name, team, role, and supporting evidence (links to the relevant messages, pages, tickets, or documents). The agent's response is mapped to a Scenarios > Return output module in a field called 'experts' so Claude can read the scenario response.
Guided by AI
Build your own with Maia
Start with an app-agnostic prompt, then let Maia guide you to the right apps and workflow.
Adapt at speed with visual-first automation and AI
Make drives efficiencies, solves problems, and speeds innovation by breaking down silos across your business.
%201.svg)
+2
Date
·
Duration
Problem
Employees who need help on a topic ask around in chat channels, scroll through old threads, browse wiki pages, and dig through tickets to guess who might know the answer. Finding the right person depends on personal networks, so questions land with the wrong people, experts in other teams stay invisible, and work stalls while people wait for answers.
.avif)
+2
Date
·
Duration
Solution
When a user asks Claude to find an expert on a topic, it calls the automation on demand with that topic, and an AI agent decides which searches to run across team chat, the knowledge base, the issue tracker, and document authorship, refining its queries as it goes. It then checks the people it surfaces against the HRIS to confirm team and role, ranks the likely experts, and returns each person's name, team, role, and supporting evidence to the assistant.
+2
Date
·
Duration
Impact
Questions reach the colleagues who actually hold the knowledge, so expertise across the company becomes easy to tap and work keeps moving instead of stalling on guesswork about who to ask.
Benefits
+2
Date
·
Duration
Faster expert discovery
+2
Date
·
Duration
Reduced misrouted questions
+2
Date
·
Duration
Increased cross team collaboration
+2
Date
·
Duration
Shorter new hire ramp
Who is this for?
Similar use cases
Find inspiration by the type of content that fits your goals.
Date
·
Duration
Route emails by inbox label
When the inbox owner applies a label to an email, the automation matches that label against a predefined routing table and runs the mapped action, either forwarding the message and its attachments to the assigned person or creating a task carrying the subject, sender, and a link back to the original message. Once the action completes, the email is archived, marked as read, and relabelled as routed. Labels with no matching rule are left untouched in the inbox.