- Getting started
- Prerequisites
- Building agents
Agents user guide
Activities
You can add and configure activities as tools directly in the Agents workspace.
Agents use Integration Service-based activities from connectors such as Box, Coupa, Microsoft Teams, Salesforce, Slack, and Zoom. Using secure, governed Integration Service connections and the field configurations described in the following sections, an agent is able to make API calls directly to a target business application. Note that not all Integration Service activities are available in Agents.
From the Design tab, under the Tools section, select Add tool, and search for activities using the search bar or select a connector from the list to see what activities are available.
Once you add an activity as a tool, you can: update its description, select a preexisting Integration Service connection or create a new one, and configure the field input options to help your agent learn how to use the activity. You can add and manage connections the same way you do in Studio for Integration Service connections, and receive notifications if the connections break or become invalid.
These are the same secure, governable connections that are configurable in Integration Service. Integration Service keeps these connections alive and will notify users if connections are broken or become invalid.
Every activity includes a default description. You can update this description to give your agent a better idea of how to use the activity during runtime. This step is not mandatory, but it is an effective way to increase the quality of outputs. It also gives your agent a better understanding of how it is supposed to use a tool for any particular use case.
Agents know what information an activity needs in order to run successfully, so you don't have to explicitly specify the inputs or outputs. By default, the agent infers the field values it requires. However, you can change the input method and select Static Value or Argument, in order to use specific data or retrieve data from the agent input arguments.
For activity fields, you can select one of the following input methods:
- Agent (default) - When selecting this option, the agent infers the field value at runtime using the Description field and other agent reasoning pertinent in determining to use the tool.
- Argument - When selecting this option, you
set the field to an agent input argument. You must first define the
argument.
Note: Use arguments for passing in runtime values from a workflow that precedes the Run Agent activity.
- Static Value - When selecting this option, you set the field to a specific, static value every time the agent runs.
Web Search and Web Reader are two first-party tools you can add to your agents to supply up-to-date context from the web or a public domain. You can use the activities for questions regarding real-time data, such as stock prices, the time, weather forecasts, or data available on a specific URL at any give time.
The Web Search tool executes a web search using natural language. Like other tools, the Search field can be inferred from instructions in the system and user prompt. For instance, you can tell your agent to get details on industry trends and competitor activities which would be used to construct a forecasting report. By offering the instruction in your prompt and adding the Web Search tool, the agent knows it needs to use the tool to access this critical, up-to-date context.
The Web Reader tool gives you the ability to extract text from a specific URL and add that as context for your agent. For instance, you have a specific parts supplier and you want to go to their web page and extract current prices for those parts. By supplying the URL directly or through the prompt, you ensure that only information from that individual URL is used for surfacing the supplier's prices for specific parts (or any other information contained in that URL).
By combining both Web Search and Web Reader, you give your agent the ability to execute research in the public domain and then use the cited sources and URLs to extract specific details.
