Agents / Bot Wizard in Tabulate Pro

Use the Bot Wizard to create or import an Agent, automatically embed it into a new Decision Flow model, and run that model on a schedule (running the agent and emailing its response to your targets). The agent accomplishes tasks on your behalf, acting like a member of staff who responds to instructions, and uses tools and reference materials selected by you to complete its work.

The Bot Wizard is available from both Discover and Tabulate.

Configuring Agents

Before you begin

• You can only create an agent for a tabulation that has already been saved. Where this is not the case, the Bot Wizard button is disabled in the ribbon.
• You can only create agents using a Bot if an LLM Provider is enabled at your tenant. Where this is not the case, the Bot Wizard button is not available on the ribbon. For more information, see AI Settings.

Opening the Bot

To open the Bot Wizard dialog, click Bot Wizard > <Print Area> from the Advanced ribbon:

Where <Print Area> means the Visual Areas, Discovery Areas, or Print Areas in the tabulation. When created, the agent will be based on this selected print area.

Creating your Agent

Choose your Starting Point

With the Bot Wizard dialog open, you can choose from the two starting point options:

Option 1: Marketplace

If you want to choose a template or open a blank bot, you should select the Marketplace tab and then:

• Blank Bot: Select the Blank option to begin with a clean, empty agent with no preset instructions.
• <Template>: Select one of the predefined, built-in templates to get started quickly. Templates typically contain detailed instructions, which might give you a head start on defining your agent.

Option 2: Custom Agents

If you want to use an Agent from Pyramid, select the Custom Agents tab. You will then need to select your agent from the standard navigation tree.

Define your Agent's Details

Whichever starting point you chose, you now need to define the Agent's details:

1. In the Bot Job panel, supply or update the following details:
   • Instructions: Agent instructions tell the agent how to behave and respond, defining both the agent's persona (what it is like) and its instructions (what it is supposed to do).
   • Tools: MCP tools offer some external capability to the agent. You can fetch data from the real-world or make use of external services. When you add an MCP tool, you are extending the agent's capabilities with services that are specific to your requirements.
   • References: References are documents (images, PDFs, spreadsheets, and so on) that the agent can use. When you add a referenced document, you are typically providing the agent with some specific domain or company information.

Tip: If you add Tools and References, you should always return to your Instructions and make sure it is clear what your agent should do with them.

2. Optionally, create a Schedule for processing your Model in the Bot Execution panel.

If you do not define any schedule details, the model will run once on creation. If you do define schedule details in the Bot Execution panel, this configuration will determine when the model is run and whether it is run once or on a recurring basis.

Tip: You do not need to define a schedule now. Once your model is created, you can return to it at any time and use the Scheduler (either in Model or in the CMS) to create a new schedule for it. For more information, see Model Scheduling.

3. Click Test to run the agent in the dialog.

The output produced, and information about the test, are displayed in a pop-up window.

4. Click Apply to create the agent and build a Decision Flow containing it.

A new Agent and Decision Flow are created alongside their discovery or tabulation. The newly created items use the Name value specified in the Instructions panel.

The Model will either run right away or will be scheduled to run according to the configuration. The last node in the Decision Flow is an Email node, meaning that, once the Model is processed, the content created by the agent is emailed to the model owner (the user who created this model).

What Next?

Currently, the model owner will receive an email notification whenever the data model is successfully processed. You can open the Decision Flow in Model and edit the Properties of the Email node to send your Agent output to a different email address or different set of email addresses.

• Click here to learn how to configure the Email node.

Bot Wizard

Bot Job

The Bot Job panel contains all of the details that allow you to define your Agent.

Instructions Tab

Agent instructions tell the agent how to behave and respond, defining both the agent's persona (what it is like) and its instructions (what it is supposed to do). You can specify the following details:

• Name: The name of the Agent. This name will be used for both the Agent object and its Model (the Decision Flow that contains the agent) when they are created.
• Persona: The character that we want the Agent to assume when it is fulfilling its instructions. This describes a simple, fictional user profile or job description that represents a typical target user's goals, behaviors, and needs.
• Instructions: This is the most important information for the Agent. It describes what the Agent needs to do; what it needs to look at, how to analyze that content, and what it needs to return. You should consider using lists or keeping your instructions in sequence to make sure that you cover everything. Also, be aware that if you use Tools or References, it might be a good idea to indicate how and when to use their content here.

Tools

MCP tools offer some external capability to the agent. You can fetch data from the real-world or make use of external services. When you add an MCP tool, you are extending the agent's capabilities with services that are specific to your requirements.

Add Tools

From the Tools page:

1. Open the Tools Marketplace.
   • If there are currently no tools selected, click Click here to start adding tools in the middle of the page.
   • Otherwise, click Add Tools at the top-right.

The Tools Marketplace opens:



2. Optionally, filter the list of available tools by typing an entry into the search field at the top-right (purple arrow above).

This is a "Contains" search, which searches for your string in the Tool Names, Tags, and Descriptions.

3. Click the Plus (+) icon (blue arrow) to choose the Tool you want to add.

If you need to remove a selection later, you can click the Minus (–) icon. If you want to remove all selections, click Clear All from the top-right.

4. Once you have selected all the Tools that you want to make use of, click Selected Tools from the top-left of the dialog (green highlight) to return to the previous page.

References

Add a Reference File

From the References page:

1. Add the file using the Drag & Drop target:
   • Drag the file from its folder location and drop it onto the target.
   • Click the target to access the Open dialog, where you can navigate to the file's folder location and select the file.

The file is added to the Uploaded Files list:



2. Repeat as required.

Remove Reference Files

• Click Remove (X) (purple arrow above) to delete a single reference file.
• Click Clear All to remove all (blue arrow) reference files.

Bot Execution

Set up the schedule configuration that allows the Bot to automatically process the data model either once or at recurring intervals. Recurring builds ensure that the model is regularly updated with the latest data. Currently, the model owner will receive an email notification whenever the data model is successfully processed. Click here to learn how to configure the email node.

The page is broken down into three sections, where you can configure the execution schedule for your model: