ThinkWithPrompt by SynotticThinkWithPrompt

Calculate how many support agents I need per shift

A staffing estimate by hour or shift from ticket volume, handle time, and service targets, with the math shown.

Customer SupportFew-ShotStandardEmailFill-in Template

The prompt

Help me estimate how many support agents I need. Contact volume: [TICKETS/CHATS/CALLS by hour or day of week, ideally for several weeks - paste data or averages] Channels: [phone / chat / email, and the volume split] Average handle time per channel: [MINUTES, including after-contact work] Service targets: [e.g. 80% of calls answered in 30 seconds, email first reply within 4 hours] Chat concurrency: [how many chats an agent handles at once] Shrinkage: [time agents are paid but not handling contacts: breaks, training, meetings, absence - e.g. 30%] Hours of coverage and time zones: [DETAILS] Current headcount and schedule: [DETAILS] Do this: 1. Calculate the workload hours needed per interval (volume x handle time), per channel. 2. For phone and live chat, estimate agents needed to hit the service target using an Erlang C approach. Explain it in plain words and show the inputs. For email, use backlog and response-time targets instead. 3. Add shrinkage to get scheduled headcount per interval. 4. Compare with my current schedule and show gaps or overstaffing by hour or shift in a table. 5. Suggest schedule changes (staggered starts, split shifts, channel moves) before suggesting new hires. Show your calculations, state every assumption, and don't invent volume numbers I didn't provide. Note how sensitive the result is to handle time and shrinkage.

Highlighted [brackets] are blanks to replace with your own details.

Fill in the blanks and use this promptMore Customer Support prompts

What to fill in

  • phone / chat / email, and the volume split
  • MINUTES, including after-contact work
  • how many chats an agent handles at once
  • DETAILS

How this prompt is built

This prompt follows the Few-Shot structure (Few-shot prompting). A few-shot prompt includes one or more worked examples of the input and the output you want, so the model can copy the pattern instead of guessing it.

Related prompts

Find more prompts like this