Claude prompt to build a Copilot Studio agent
A prompt for a Microsoft Copilot Studio agent: its purpose and users, topics and trigger phrases, knowledge sources (SharePoint, websites, files) with their permissions, the actions and flows it can call, authentication, and the channel it publishes to.
Tuned for Claude · structured role / context / task / output
Open in the builder →Ready-to-use prompt
# Role You are an experienced AI systems designer who writes system prompts and operating instructions for AI agents: clear scope, explicit tool rules, recovery paths, and a definition of done. # Context Design a Copilot Studio agent for the HR team that answers policy questions from the HR SharePoint site and opens a ticket when it cannot answer. # Task Write the operating instructions for the agent described in the context above: its scope, how it uses each tool, how it verifies results and recovers from failures, how it manages context over the run, and what counts as done. # How to approach this You reason carefully on your own. Work the problem through internally and return a clear, well-structured answer — there's no need to spell out scratch work in <thinking> tags. Use that internal reasoning to catch edge cases before you commit, and scale the depth of thought to the difficulty of the task. - Define the scope first: what the agent does, what it must never do, and who it serves. - End with a testable definition of done; the agent should be able to check it against its own output. Before you finalize, verify that every tool has a stated purpose, a success check, and a failure path; the completion criterion is testable; nothing in the instructions conflicts with the autonomy level. # Constraints - Keep the instructions as short as they can be while covering scope, tools, recovery, and completion; every extra rule competes for attention. - Use clear markdown sections and headings. Favor well-structured, thorough output over terse output. - If a critical detail is missing or genuinely ambiguous, ask a brief clarifying question before continuing; otherwise state your interpretation in one line and proceed. - Do not open with "I'd be happy to help" or any variant. Just start. - Do not add "Note:", "It's worth mentioning", or "I should point out" framing — put facts in the deliverable, not in disclaimers around it. - Treat clearly benign tasks as safe and complete them directly. - Deliver the result directly — no apologies or meta-commentary about the prompt itself. # Output format Return only the requested output. If multiple distinct variants would clearly help, label them (e.g., "Option A", "Option B"). # Done when - the output fully answers the goal in the Context section with no missing parts
Customize this prompt
Answer a few quick questions and Promptivo re-tunes the prompt above to your exact situation.
Start the interview →Why this prompt works
Copilot Studio agents answer from knowledge sources with the user's permissions, so the prompt asks which sources, who can see them, and what the agent must refuse.
Topics and actions are where behavior is defined. The prompt asks for the trigger phrases, the flows or connectors the agent calls, and what it does when a request falls outside its scope.
Publishing decides the experience. The prompt asks for the channel (Teams, web, Microsoft 365 Copilot) and the authentication model.
Using this prompt in Claude
For copilot studio agent, Claude is a strong choice — it's especially good at careful step-by-step reasoning and cleanly structured long-form writing. Promptivo formats this prompt the way Claude works best: explicit step-by-step thinking and clearly delimited output sections.
Paste it into claude.ai or the Claude desktop app, then replace any bracketed details with your own. Claude sometimes opens with caveats, so this prompt tells it to lead with the answer and keep each section clearly delimited.
Tuned for Claude: how it differs
| Model | What Promptivo changes |
|---|---|
| ChatGPT | Concise instructions, strict format adherence, no preamble. |
| Claude | Explicit step-by-step thinking and clearly delimited output sections. |
| Gemini | Precise phrasing with brief reasoning cues where they improve accuracy. |
| Copilot | Office-ready output that pastes cleanly into Word, Outlook, and Excel, with tables and numbered steps. |
Questions, answered
- What is Copilot Studio?
- Microsoft's low-code tool for building agents and copilots that answer from knowledge sources, follow authored topics, and call Power Automate flows or connectors, published to Teams, websites and Microsoft 365 Copilot.
- How do I give a Copilot Studio agent company knowledge?
- Add knowledge sources such as SharePoint sites, public websites or uploaded files, and use generative answers. Access respects the user's permissions when authentication is on.
- Can a Copilot Studio agent take actions?
- Yes. Add actions backed by Power Automate flows, connectors or prompts, and define the inputs the agent collects before calling them. The prompt asks for each action and its guardrails.
- Is Claude good for copilot studio agent?
- Yes. Claude handles copilot studio agent well thanks to its careful step-by-step reasoning and cleanly structured long-form writing, and Promptivo tunes the prompt to match — explicit step-by-step thinking and clearly delimited output sections. Paste it into claude.ai or the Claude desktop app.