Prompts for the Assembled MCP server

Plans and permissions:

• Plan: Pro or Enterprise plan
• Read Assembled data through MCP: Admin role, or a custom role with Assembled MCP set to Can access all data via the MCP or Can access and make changes to all data via MCP
• Create forecast adjustments and publish overtime or voluntary time off through MCP: Admin role, or a custom role with Assembled MCP set to Can access and make changes to all data via MCP

Use these tips and example prompts to get precise answers about your schedules, forecasts, adherence, and performance from an AI assistant connected to the Assembled MCP server.

To connect an AI assistant first, see Assembled MCP server setup.

Write good prompts

You don’t need metric names or filter syntax: plain English works, and more context gets you more precise answers.

• Use specific dates, such as “the week of June 9” or “June 1–14”, instead of “last week”.
• Name the channel or queue, such as “on chat” or “for the phone queue”.
• Start broad, then narrow down. “What metrics can I analyze?” is a good first prompt.
• Ask follow-up questions. Your assistant keeps the context of the conversation.
• If your assistant isn’t using Assembled, add “Use Assembled” to your prompt.
• If a query returns no data, the metric may not be available, or the dates may be before October 2025. Try rephrasing it or changing the dates.

Compare forecast and actual results

Comparing what you planned with what happened shows whether a service gap came from the forecast, from staffing, or from unexpected demand. You can compare volume, handle time, staffing (required and scheduled), and service level.

• Name a channel, such as email, chat, or phone. There’s no combined view of all channels.
• If you’re not sure which channels you use, ask, and your assistant looks them up.
• Optionally, name a queue. Without one, all queues are combined.
• Use time ranges of up to about 6 months. For longer analysis, ask for metrics instead.
• Results use your primary schedule, not test schedules.

Results are grouped by the length of the time range:

For example: “How did actual email volume compare to forecast last week?” or “What was the staffing gap for the chat queue over the past two weeks, and where was it most short?”

Keep in mind: A staffing gap isn’t always a forecasting problem. If volume was on forecast but you were still short, check adherence and scheduling. A volume miss can come from a launch, an outage, or a campaign.

Example prompts

Quick lookups

• “What was our SLA last week by team?”
• “Show handle time by queue for the past 7 days.”
• “Who is on the schedule tomorrow for the Billing queue?”
• “How much overtime does each team member have this week?”
• “Who changed this team member’s schedule yesterday?”

Daily and weekly check-ins

• “Did all queues hit SLA yesterday?”
• “Show SLA, AHT, and adherence for each team this week, ranked.”
• “Summarize SLA performance for the week of June 9 for a leadership update.”

Analysis

• Diagnose an SLA miss: “Where and why did we miss SLA last week? Break it down by interval and tell me whether it was shrinkage, AHT, or volume.”
• Plan a scenario: “If volume jumps 25% next week, where do we go into deficit, and what RPH do we need to still hit SLA?”
• Oversee vendors: “Which BPO partner is delivering the best cost per CSAT point this quarter?”
• Combine systems: “Pull hire dates from our HR system. If I exclude team members with less than 90 days’ tenure, does the AHT increase persist?”
• Investigate intraday: “Chat actuals are well below forecast. Find anything in the last 24 hours that explains it.”

Actions

These prompts change data, so your assistant asks you to approve them first.

• “Apply a +40% volume adjustment to chat for Sunday 1 PM to 11 PM ET across all US queues.”
• “Publish overtime on phone for every interval next week where the forecast exceeds scheduled coverage by more than 10%.”
• “Offer voluntary time off for any 30-minute interval this week where email is more than 15% overstaffed.”