- Introduction
- 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
- Getting Started with UiPath Maestro Flow
Build, evaluate, and publish a coded LangGraph agent using the UiPath CLI and coding agent skills.
In this lab, you will install the UiPath CLI and coding agent skills, then use your coding agent to build, run, and evaluate a LangGraph agent. You will do the following:
- Install the UiPath CLI and coding agent skills.
- Scaffold a local project and build a LangGraph agent guided by skills.
- Add a live external lookup tool to the agent.
- Run and evaluate the agent locally.
- Connect the project to UiPath Studio Web and push your first version.
By the end, you will have a working LangGraph agent built through your coding agent, guided by UiPath skills, with evaluation traces flowing to Studio Web.
There are three approaches to create UiPath agents. This uses the LangGraph SDK; you can also create agents using the low-code Agent Builder and using the UiPath CLI.
Estimated time: 45–60 minutes
What you are building
This lab walks you through building a quest intake classifier for a fictional adventurer's guild: a coded LangGraph agent that reads a quest description and sorts it into one of four difficulty tiers.
It starts as a simple, single-node classifier so the focus stays on the CLI workflow, not the domain logic. Then you give it a tool so it can check its answer against a live external API before finalizing a tier, instead of guessing from vibes alone.
Here is the full design of what you are building:
| Component | Details |
|---|---|
Input: description | string; the incoming quest description |
Output: tier | A Literal type constrained to exactly "Trivial", "Standard", "Heroic", or "Legendary", not a plain string, so the model cannot emit an out-of-vocabulary tier |
Output: reasoning | string; the agent's explanation for the tier it chose |
Tool: get_challenge_rating | A LangGraph tool, called only when a quest names or implies a specific creature, that looks up its challenge rating from the Open5e System Reference Document (SRD) API and cites it in the reasoning |
Why add a tool at all? A driving reason to run a LangGraph agent on UiPath, instead of a low-code agent, is complex Python logic that can call out to external systems, not just classify text. The tool step in this lab demonstrates that: the agent decides at runtime whether a quest needs verification, calls a live API, and reasons over the result.
Prerequisites
- CLI version - validated against UiPath CLI v1.201.0 (installed in Step 1). Different versions may behave differently; report drift with
uip feedback send. - UiPath account - sign up or log in to UiPath Automation Cloud before starting.
- Node.js 18+ - required to install the UiPath CLI. Check with
node --version. Download from nodejs.org if needed. - VS Code with a coding agent (Claude Code, Copilot, or Cursor). The lab instructions use Claude Code, but any supported coding agent will work.
- Bash terminal - the commands in this lab use Bash syntax. In VS Code, open a new terminal and select Git Bash (or equivalent) as the terminal type. PowerShell and CMD syntax differ and may cause unexpected errors.
- uv - a fast Python package manager. Install it with:
or see the uv installation docs for other options.
pip install uvpip install uv - Admin rights - installing global npm packages and Python dependencies requires admin/elevated permissions. If you are on a work laptop with restrictions, confirm you can install packages before starting, or work with your IT team in advance.
No existing knowledge of UiPath is required for this lab, but it will make it go faster.
Two "agents" in this lab. "Coded agent" is UiPath's term for a Python agent deployed on the platform; this lab builds one using the LangGraph SDK. The lab instructions also reference your "coding agent" (Claude Code, Copilot, Cursor) to help write the Python code.
When the instructions say "ask your coding agent," they mean your integrated development environment (IDE) assistant; when they say "run the agent" or "your LangGraph agent," they mean the UiPath agent being built.