Researcher

The Researcher is an agent that performs deep, structured research on a given topic by gathering insights from web and market sources. Each result includes citations and source links to support accuracy and transparency.

After you enter a topic or a question, the agent:

Conducts multi-query web searches.
Retrieves data from analyst and industry sources (for example, Statista, MarketsandMarkets, McKinsey & Company).
Generates a detailed report with key takeaways, references.

When to use

Use the Researcher for the following business scenarios:

Market sizing and competitive intelligence.
Trend discovery for campaign planning.
Analyst-style research summaries for executive or sales enablement.

Edit the configuration

Before running the Researcher, review and edit its configuration to customize how it behaves and generates responses.

Configuration determines what the agent does and how it produces content, and is required to align the agent with your brand, audience, workflows, and specific needs.

Before you begin

Make sure you have a Builder License assigned to your user account. This license is required to edit agents.

To edit the configuration:

In the navigation menu, click Agentic. Then, in the left sidebar, select Agents.
On the Agents page, find Researcher .
Click the actions menu > Edit.
Review and configure each tab as needed to adjust how the agent works:
- Overview - view the agent's basic information, how it works, and inputs required to run it. This tab is read-only.
- Instructions - define guidance that shapes how content is generated. For example, you can specify target audiences, channels, languages, and formats.
- Schemas - define structured JSON output formats. For example, you can add schemas for blog posts, email content, or social media posts.
- HTML Templates - define how generated content is formatted and displayed in previews. Templates typically correspond to the defined schemas.
- Workflow - view the agent’s execution workflow, including all processing steps. This tab is read-only.
Click Save Changes. Return to the Agents page and run the agent.

Run the agent

Use the Researcher to analyze a topic and generate research output.

To run the agent:

In the navigation menu, click Agentic. Then, in the left sidebar, select Agents.
On the Agents page, find Researcher.
Click the agent's card. The agent opens on a new page displaying its details.
In the Input section, enter a specific topic to research.

Example: Gen Z consumer behavior trends in online shopping across North America.
Click Start to run the agent.

Tip

This step might take some time. You can leave the page and track progress at any time in Spaces.

The agent analyzes your input and opens a new space for the run.
When processing is complete, the results appear in the space, which includes:
- Space overview - provides a snapshot of the space, including:
  Summary - displays totals such as the number of artifacts created, total time spent, and data sources used.
  
  Artifacts - shows a thumbnail view of all generated artifacts. Click an artifact to open it.
  
  Completed Tasks - lists finished steps with execution times.
- Chat - opens a chat interface within the space where you can continue collaborating with AI. All artifacts stay in the same thread, so you can build on previous outputs without losing context.
  
  You can use the same options available in the Chat interface. See Start a chat within a space for details.
- Agent task list - displays a step-by-step view of tasks performed by each agent, including time spent on every step.
- Add Agent - lets you add another agent to your current workflow. Agents run sequentially in the same space and share context, so you can refine and expand work without starting over.
  
  For example, after running the Researcher agent, you can add Bulk Content Generator to build on the previous output. See Run additional agents within a space for details.
- Artifacts - displays all generated artifacts grouped by task or agent. Click an artifact to open or manage it. See Manage an artifact for details.
- Context - shows the inputs used for the run, including selected sources and attachments.
Important

Always review AI-generated results carefully and validate key information before using it.

Next steps

You can do the following:

Add collaborators to this space.
Manage artifacts generated during the run. You can view, review, and refine them as needed.
Chat within the space to continue working with AI.
Run additional agents for additional tasks.
Convert a generated artifact into a SitecoreAI item.
Click Complete to finish the task and mark the space as Finalized.

Do you have some feedback for us?

If you have suggestions for improving this article,