- Getting started
- UiPath Agents in Studio Web
- UiPath Agents in Agent Builder
- UiPath Coded agents
Agents user guide
Agents can use Integration Service activities as tools.
Through 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.
- Start with an RPA workflow to fetch a file and pass it as an input to the Run Agent activity.
- Use an RPA workflow as a tool in your agent to pass a file as an input or output a file to the agent.
- From the Design tab, under the Tools section, select Add tool.
- In the Toolbox:
- Search for an activity using the search bar, or
- Select Activity and browse by connector. Selecting a connector reveals the list of supported activities.
- Once you add an activity as a
tool, you can:
- Edit the tool name and description.
- Select a preexisting Integration Service connection or create a new one.
- Configure the input fields to teach your agent how to use the activity.
Each activity comes with a default description, which you can customize to better guide your agent during runtime. While optional, this step enhances output quality and helps the agent understand how to use the tool for specific use cases.
Agents can automatically infer the information needed to execute an activity successfully, so you typically don't need to define input or output values manually. By default, agents determine the appropriate field values at runtime based on the tool’s description and context.
However, you can override this behavior for any field by selecting a different input method using the context menu. The available input methods are:
- Prompt (default) – The agent infers the field value at runtime using the tool’s description and other relevant information.
- Argument – The field is populated using an agent input argument. You must define the argument beforehand. This option is useful for passing data from a preceding workflow into the agent via the Run Agent activity.
- Static Value – The field is set to a fixed value that remains the same every time the agent runs.
- Cascading fields cannot be set to Prompt input method. These are fields where selecting a specific value (e.g., an issue type in Jira) changes the structure of the remaining fields in the activity. Because the tool schema cannot dynamically adjust at runtime, agents cannot infer values for such fields.
- Other fields default to Prompt and can be LLM-inferred at runtime. However, you must ensure the agent has access to the necessary context (e.g., via prior tools, prompt wording, or arguments) to infer those values correctly.
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.
Web Search
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.
Web Reader
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.
