Body
Overview
Ever wonder why one Copilot Cowork request uses a handful of credits while another burns through hundreds? It comes down to task complexity. Copilot Cowork sorts every request into one of three categories—Light, Medium, or Heavy—depending on how many sources it needs to pull from, how much reasoning it has to do, and how many deliverables it produces. The bigger the ask, the more credits it uses. Knowing which category your task falls into in advance can help you plan your workload, manage your credit budget, and avoid surprises on your bill. Below, we'll walk through each tier, share real prompt examples, and show you the estimated credit range for each—so you can get the most value out of every request.
Copilot Cowork Task Types
| Task Type |
Description |
Characteristics |
Prompt Example |
Est. Copilot Credits |
| Light Tasks |
Leverages a handful of knowledge sources for a light reasoning scenario like a summary, usually resulting in one short deliverable. |
- Few sources
- Light reasoning
- 1 or fewer outputs
|
"Create a weekly status update for my team that runs every Monday morning - including my top-of-mind priorities and a short list of key executive meetings pulled from my calendar." |
100 – 300 |
| Medium Tasks |
References many sources over varying time frames, uses structured reasoning, and produces multiple deliverables. |
- Many sources
- Structured reasoning
- 2+ outputs
|
"Help me prepare for a customer meeting by pulling relevant emails, calendar items, and recent files into a briefing doc based on our template, an Excel overview of sales and sales trends, and a client-ready presentation." |
300 – 700 |
| Heavy Tasks |
Requires deep analysis and broad source aggregation over long time frames, generating many outputs. |
- Broad aggregation
- Deep reasoning
- Many outputs
|
"Analyze 6 months of exported product usage data to understand usage patterns, classify prompts, and produce a leadership-ready report..." (shortened) |
>700 |