--- title: "Set up your first virtual employee | Tidy" description: "Create a workshop, give your employee a role, choose a harness and connect a model. Follow the narrated Tidy setup guide and review the deployment." url: https://www.tidy.engineering/virtual-employees last_updated: 2026-10-13T12:38:24.000Z --- 04 / Virtual employees # Your first employee. Let's set it up. Give it a role, choose where it works and decide how it uses AI. Watch the whole setup, from adding a workshop to Penny starting as project coordinator. The real product, narrated. Waits are trimmed, credentials hidden, people fictional. ![Penny's role and instructions in Tidy](https://www.tidy.engineering/img/c191/video-poster.webp) Playing loads YouTube. [Watch on YouTube](https://www.youtube.com/watch?v=8KSf6ak_9So) **Read the narration** Here's how to set up a virtual employee in Tidy. We'll create a workshop, give Penny a role, and deploy her. A workshop is the computer where an employee runs. Use a machine you already have, or choose a supported cloud host. For this demo, we're using an isolated Linux machine. Give it a name and choose its operating system. Then run the setup command on that computer. The command contains an enrollment credential, so we've hidden it here. The installer checks the machine and starts the workshop. When it reports online, we can continue. We've cut out the installation wait. Now create Penny. Give her a name, a role and instructions. She coordinates our store opening, checks dates and owners, and asks before contacting people or changing deadlines. An employee can run on Tidy, with no machine to manage. Choose a workshop when the work needs local files and tools. We're assigning Penny to the workshop we just set up. Next, choose a harness. That's the software that runs the employee. We're using Pi. Other supported choices include Claude Code and Codex. The model connection is a separate choice. With Tidy inference, Tidy supplies the models and manages access. You don't need to bring a provider key. With provider sign-in, you authorize a supported account through its login flow. OAuth is different from an API key. What you can use depends on the provider, the harness and your plan. Your provider's limits still apply. Use the sign-in controls for accounts and keys. Don't put passwords in an employee's instructions. These model choices don't change what the employee can access in your workspace. Choose a project folder and deploy. Tidy asks us to approve the harness installation. We confirm our identity before it runs. Tidy installs the harness, applies the employee's configuration and checks the result. We've shortened the waiting time here. Penny is now deployed. Start with a small task and review what comes back. Her identity and work stay in Tidy if you move her to another workshop. Recorded on a Linux test machine. Your own computer or server follows the same steps. The two things you're creating ## An employee. A place to work. Penny is the employee. The workshop is the computer where Penny runs. ### The employee keeps the role Name, instructions, skills, conversations and backlog live in Tidy, so they move when the machine changes. ### The workshop supplies the machine Files, tools and somewhere to run. Several employees can share one. ### You can start without your own machine "Run on Tidy" hosts it for you. Use your own workshop when the job needs your files, a browser or local tools. The setup ## One decision at a time. You can revise the employee's setup later. Start with a narrow job and only the access it needs. 1. ### Add a workshop Name the machine and pick its operating system. Tidy gives you one setup command. Treat it like a password. 2. ### Wait for it to report online Run the command on that computer. The workshop shows up in Tidy when it reports in. 3. ### Describe the employee's job Name, role, instructions. Here Penny coordinates a store opening and asks before contacting anyone or moving a deadline. 4. ### Choose a harness and sign-in method The harness is the software that runs the employee: Pi, Claude Code, Codex and others. The model connection is a separate choice. 5. ### Deploy and check the result Put the employee on the workshop, finish any sign-in Tidy asks for, and check it reports ready. The workshop is online View full size ![The actual demo workshop reporting online in Tidy.](https://www.tidy.engineering/img/c191/workshop-online.webp) How it gets its AI ## Tidy inference or your provider account? Three ways to reach a model. None of them changes what the employee can see or do. ### Tidy inference Tidy handles the model. Nothing extra to bring. Usage comes with your Tidy plan. ### Provider sign-in Sign in with your own provider account. Tidy never sees your password. Your provider's plan and limits apply. ### Provider API key Bring a key from a supported provider. The provider bills usage to that key. Options depend on the harness. The walkthrough uses Pi with Tidy inference. Start with a useful task ## "Penny, draft the opening-week brief." Point it at the project and say what you want back. Review the draft, then sharpen the instructions. ### Access Only the records and tools the job needs. ### Approval Anything sensitive or outward-facing waits for a person. ### Activity Read its conversations and check its work. Penny / Role and instructions View full size ![Penny's name, role and instructions in the actual employee setup flow.](https://www.tidy.engineering/img/c191/employee-ready.webp) Virtual employees need Plus. Model and hosting costs depend on your setup. [See what you can work on together](https://www.tidy.engineering/collaboration) Keep going [Memory Find anything.](https://www.tidy.engineering/memory) [Automation Hand off repeat work.](https://www.tidy.engineering/automation) [Collaboration Work on the originals.](https://www.tidy.engineering/collaboration) [Virtual employees Set up your first one.](https://www.tidy.engineering/virtual-employees) Tidy · Private beta · Fictional demo content [Back to the thread](https://www.tidy.engineering/#thread)