Here, we explain how to determine whether a declarative agent is the right choice for customizing Microsoft 365 Copilot. We list criteria that indicate whether declarative agents meet your goals.

Decision criteria

Declarative agents help you extend Microsoft 365 Copilot with agents tailored to specific scenarios, without requiring a lot of code. Cases where declarative agents aren’t the best choice generally involve a need for deeper customization and flexibility offered by the platform.

Factor	Description
Scenario	The key question to ask when considering declarative agents is: “Do I have a specific subject or task that I want to optimize?” Declarative agents work well when you know the scenario you want to optimize.
Orchestrator and model	Declarative agents use the same orchestrator and model as Microsoft 365 Copilot. Reusing the existing infrastructure and controls provides a consistent experience for end users. If you require custom orchestration and/or a different language model, then a declarative agent isn’t an option: you should consider building a custom engine agent instead.
Data sources	The next consideration is data sources. Declarative agents work well when the information relevant to your scenario is available within Microsoft 365. If you need to ingest data into Microsoft 365 from an external system, you can use a Copilot connector. If you need to interact with external systems in real time, you can use a custom action.

Applying the criteria

Declarative agents work best when you want to reuse the same orchestrator and foundation model as Microsoft 365 Copilot.

Our fictional IT support team needed a way for employees to find answers to common IT support questions and to create support tickets when they couldn’t find the answers they needed.

Our goal was to decide whether this scenario was a good fit for a declarative agent. To make our decision, we must analyze each task according to the three criteria we identified: scenario, orchestrator and model, and data sources.

Do we know the scenario we want to optimize?

Yes. Employee IT support self‑service.

Do we need a custom orchestrator and model?

No. The orchestrator and model from Microsoft 365 Copilot can summarize and transform information from documents.

Do we know the authoritative data sources?

Yes. We know that the knowledge base articles are stored as PDFs in SharePoint Online.
Although the support ticketing system data isn’t stored in Microsoft 365, we can create a custom action to interact with that system.

A declarative agent is a good choice for our fictional IT support team.
A declarative agent is a good choice if:

• we know the scenario we are optimizing for,
• the orchestrator and model provided by Microsoft 365 Copilot are suitable for the task,
• and the grounding data already exists in Microsoft 365.

Guidance summary

The following flowchart summarizes the key questions to ask when considering whether to use declarative agents.