- Overview
- Getting Started with UiPath Agents
- Getting Started with UiPath Agents using LangGraph
- Building a Low-Code Agent in Studio Web
- Adding Tools to Your UiPath Agent
Extend a low-code UiPath agent with an API Workflow tool that queries the D&D 5e SRD at runtime.
This lab builds part of UiPathfinder, a D&D-themed reference application on UiPath. It extends an agent built in the Getting Started with UiPath Agents lab. You build a live API connector that searches the D&D 5e SRD (System Reference Document), then give your Monster Selector agent that connector as a tool. The agent uses it autonomously at runtime: deciding what to search for, calling the API, and selecting the best match from the results.
By the end you will have UiPathfinder.QuestParser: an agent that receives only a quest description, decides what to search for, calls the Monster Query tool, and returns the selected monster's key fields, with no pre-populated list required.
Without a tool, the agent depends on the caller to pre-fetch candidates and pass them in as data. Adding a tool changes that: the agent decides at runtime what to search for, calls the API, and reasons over live results. This is the pattern behind most production agent workflows; the agent's value comes from its ability to fetch and reason, not just classify what it is handed.
You will do the following:
- Build a Monster Query API Workflow that calls the D&D 5e SRD.
- Connect it to your Monster Selector agent as a tool.
- Update the agent contract to reflect the new capability.
- Test the full tool-using agent end-to-end.
Estimated time: 30-45 minutes
What you are building
| Component | Details |
|---|---|
| API Workflow | Accepts searchName (string), calls the Open5e D&D 5e SRD API, returns monsterResults array |
Agent input: questDescription | string; the quest description. The agent fetches its own candidates via the tool |
Agent output: monsterIndex | string; slug identifier of the selected monster |
Agent output: monsterName | string; display name of the selected monster |
Agent output: monsterType | string; creature type (for example, beast, undead, dragon) |
Agent output: monsterCr | string; challenge rating |
Agent output: monsterReasoning | string; the agent's explanation of why it selected this monster for the quest |
Prerequisites
- Studio Web - runs in your browser; no desktop installation required. Open Studio Web in Chrome, Edge, or Firefox before starting.
- UiPath account - sign up or log in to UiPath Automation Cloud before starting.
- Node.js 18+ - required to install the UiPath CLI. Install from nodejs.org if needed.
- UiPath CLI v1.1+ - required to deploy the starter. Check with
uip --version. - A Monster Selector agent in Studio Web - this lab builds on the agent from Getting Started with UiPath Agents. If you completed that lab, your agent is already there. If not, deploy the starter:
git clone https://github.com/cliff-simpkins/UiPath-Workshops.git
cd UiPath-Workshops/starters/monster-selector
uip login
uip solution upload .
git clone https://github.com/cliff-simpkins/UiPath-Workshops.git
cd UiPath-Workshops/starters/monster-selector
uip login
uip solution upload .
Open Studio Web and confirm MonsterSelector appears in your workspace before beginning Step 1.