call-prep

The call-prep skill is designed to automate the time-consuming process of gathering intelligence before high-stakes customer or prospect calls. Targeted at sales professionals, account managers, and customer success teams, this tool synthesizes fragmented data from your CRM and engagement platforms into a structured, scannable briefing. By leveraging Common Room signals, it identifies recent product interactions, renewal timelines, and potential risk indicators such as support tickets or declining usage metrics. This allows you to walk into every discovery call, demo, or QBR with a deep understanding of the customer's current state and sentiment.

• Automatically aggregate account-level insights including recent news, executive changes, and funding milestones.

• Extract specific signal data from Common Room to identify high-intent buying behaviors or engagement patterns.

• Perform contact research to clarify roles, influence, and personal engagement history for each meeting participant.

• Generate custom talking points and anticipate objections based on historical interaction logs, such as Gong recordings or previous meeting notes.

• Incorporate calendar integration to automatically surface meeting agendas, upcoming schedules, and participant details when available.

• Enhance intelligence with a web-based recency check to capture events occurring since the last data synchronization.

• Ensure you provide a clear company name; specifying attendee names significantly improves the depth of the output.

• When the tool returns sparse data, it will provide an honest summary rather than fabricating information, helping you maintain credibility.

• The output is formatted as a professional brief, including meeting context, company snapshots, attendee profiles, and recommended outcomes.

• Use this skill to minimize research time, ensuring your prep process stays within a five-minute window while maintaining high signal quality.

• Always prioritize real data signals to ground your conversation; the skill is designed to flag unknowns explicitly rather than filling gaps with generic filler content.