How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

PM Refresh M365 Copilot Agents - Prompt

Name: PM Refresh M365 Copilot Agents
Author: NataliaRamos

Prompt file imported from NataliaRamos/commerce-docs (.github/prompts/users/johnsmit/PM Refresh M365 Copilot Agents.prompt.md). Copyright stays with the author.

Prompt Name: PM Refresh M365 Copilot Agents

Instructions to update the M365 Copilot Agents table

This prompt references this page: docs/ai_productivity/AI Catalog/M365 Copilot Agents.md

Task #1: Update the M365 Copilot Agents table

We will update the M365 Copilot Agents table located in this document:
This table represents a catalog of the top 50 M365 Copilot Agents created by individuals in C+E based
The format of this table shall remain the same.
It consists of the following columns: Icon, Agent Name, Description, Creator, Users, Created Date
Data for this table can be found in the data/M365_Copilot_Agents.csv file.
Update the date for Last Refreshed to the current date.
Please refresh the data in this table using the following instructions:
1. Icon = agentIcon: Is a 32x32 image that represents the agent. You will find the icons in the images/copilot_agent_icons directory.
2. Agent Name = agentName: The name of the agent. These should be clickable images using agentURL.
3. Description = agentDescription
4. Creator = agentCreatorName
5. Users = userCount
6. Created Date = agentCreatedDate: The date the agent was created.
Limit results to the top 50 agents based on UserCount

Task#2: Update the Copilot Prompt section

The Copilot Prompt section is located at the bottom of this document.
This section contains the PM Refresh M365 Copilot Agents prompt instructions.
The instructions are in a code block and should be formatted as a code block.
Update that code block based on the instructions above.

Install PM Refresh M365 Copilot Agents and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

{ "prompt": "## Prompt Name: PM Refresh M365 Copilot Agents\n### Instructions to update the M365 Copilot Agents table\n- This prompt references this page: docs/ai_productivity/AI Catalog/M365 Copilot Agents.md \n\n**Task #1: Update the M365 Copilot Agents table**\n- We will update the M365 Copilot Agents table located in this document: \n- This table represents a catalog of the top 50 M365 Copilot Agents created by individuals in C+E based\n\n- The format of this table shall remain the same.\n- It consists of the following columns: Icon, Agent Name, Description, Creator, Users, Created Date\n- Data for this table can be found in the data/M365_Copilot_Agents.csv file.\n- Update the date for Last Refreshed to the current date.\n \n- Please refresh the data in this table using the following instructions:\n 1. Icon = agentIcon: Is a 32x32 image that represents the agent. You will find the icons in the images/copilot_agent_icons directory. \n 2. Agent Name = agentName: The name of the agent. These should be clickable images using agentURL.\n 3. Description = agentDescription\n 4. Creator = agentCreatorName\n 5. Users = userCount \n 6. Created Date = agentCreatedDate: The date the agent was created.\n \n- Limit results to the top 50 agents based on UserCount\n\n**Task#2: Update the Copilot Prompt section**\n- The Copilot Prompt section is located at the bottom of this document.\n- This section contains the *PM Refresh M365 Copilot Agents* prompt instructions. \n- The instructions are in a code block and should be formatted as a code block.\n- Update that code block based on the instructions above.", "variables": [], "notes": "Prompt Name: PM Refresh M365 Copilot Agents ### Instructions to update the M365 Copilot Agents table - This prompt references this page: docs/ai_productivity/AI Catalog/M365 Copilot Agents.md", "metadata": { "source": { "provider": "github-prompts", "repository": "https://github.com/NataliaRamos/commerce-docs", "path": ".github/prompts/users/johnsmit/PM Refresh M365 Copilot Agents.prompt.md", "ref": "24ccc6c10af133ff3e81701916e98d4fe1ae09dc", "url": "https://github.com/NataliaRamos/commerce-docs/blob/24ccc6c10af133ff3e81701916e98d4fe1ae09dc/.github/prompts/users/johnsmit/PM Refresh M365 Copilot Agents.prompt.md", "key": "NataliaRamos/commerce-docs/.github/prompts/users/johnsmit/PM Refresh M365 Copilot Agents.prompt.md" } } }

PM Refresh M365 Copilot Agents

About

Prompt Name: PM Refresh M365 Copilot Agents

Instructions to update the M365 Copilot Agents table

Use it

Install PM Refresh M365 Copilot Agents and it becomes one more candidate the router can pick - when it fits.

What it costs to adopt - in engineering time.

One base URL

No vendor lock-in

Failover built in

Manifest

Reviews