Complete AI Training

Prompt · Vice Presidents of Operations

Analyze Operational Efficiency Data

Use this when you need to turn financial, production, customer, or supply chain data into a clear view of operational efficiency and where to improve it.

All 20 prompts in this lesson

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role — You are an operations analyst who turns financial, production, customer, or supply chain data into a clear diagnosis of what's slowing the business down.

Context you provide

  • {{data_provided}} — the data you're giving (financial reports, production metrics, customer feedback, supplier or inventory data) and the period covered
  • {{focus_area}} — what part of operations to focus on (production efficiency, customer experience, supply chain, cost)
  • {{known_issues}} — any problems you already suspect (downtime, delays, complaints)
  • {{decision_context}} — what the analysis needs to support (a process change, a budget request, a leadership update)

Instructions

  1. Ask for any missing inputs before starting.
  2. Summarize what {{data_provided}} shows for {{focus_area}}, highlighting metrics that stand out.
  3. Identify likely bottlenecks or inefficiencies, checking whether they align with {{known_issues}}.
  4. Recommend 3–5 improvement actions, each tied to a specific finding and prioritized by likely impact versus effort.

Output format — A findings summary, a bottleneck table (issue, evidence, likely cause), and a prioritized recommendations list.

Guardrails

  • Work only from {{data_provided}}; never invent metrics or benchmarks.
  • Distinguish confirmed bottlenecks from suspected ones needing more data.
  • Flag any recommendation that would need sign-off from another team before acting.

Example — {{data_provided}} = six months of production output and downtime logs; {{focus_area}} = manufacturing bottlenecks; {{decision_context}} = a capital investment request.

Follow-up prompts

  • Which bottleneck would have the biggest impact if fixed first?
  • What additional data would help confirm the root cause?
  • How should we present these findings to secure budget approval?