This guide takes you from an empty workspace to a live AI Coworker you can chat with — a simple support assistant on NeoGPT. It takes about ten minutes.
For everything each tab can do, see the AI Coworkers section. For a richer, multi-channel build with skills, memory, and human approvals, see the worked example.
Before you start
You need access to a workspace with permission to create and publish Coworkers, and at least one foundation model enabled in the workspace. If either is missing, ask your workspace administrator.
Step 1 — Create the Coworker
In the left sidebar, open Coworkers and click Create Coworker. On the welcome screen, click Let’s get started.
Step 2 — Describe who it is
On Basics & Identity, fill in the five required fields:
- Name —
Ada - Tone — Friendly
- Job role —
Support Assistant - Foundation model — any model enabled in your workspace
- Objective —
Answer common questions clearly, and hand off to a human when unsure.
Optionally add a Persona & principles note such as “Be concise and always offer a next step.” Then click Next — your Coworker now exists as a draft.
Step 3 — Give it a channel
On the Channels step, add NeoGPT. Give it a name and a welcome message such as Hi! I'm Ada. What can I help you with?. NeoGPT is internal chat and needs no credentials, so it is the quickest way to test.
Step 4 — Add a skill (optional)
On the Skills step, switch on one ready-made skill your workspace offers — for example a web-search or knowledge tool. If none are available yet, skip this; you can add skills any time.
Click Skip for now on the remaining steps, then Complete on the last one to close the wizard.
Step 5 — Publish
Open Ada from the Coworkers list, click Publish, and confirm. Ada is saved as a version, deployed, and becomes Active.
The NeoGPT channel you added in Step 3 starts switched off, because channels can only be enabled once a Coworker has been published. Open the Channels tab and switch NeoGPT on — Ada is now ready to use.
Step 6 — Try it out
Open Ada in NeoGPT and send a message. Then open the Traces tab on Ada’s page to see how it handled the request — which skills it used and what came back.
What’s next
That’s a working Coworker. From here you can:
- Add more channels — Microsoft Teams or Outlook email.
- Give it more skills, including agents you have built in other builders.
- Turn on memory so it remembers across conversations.
- Add guardrails and approvals for sensitive actions.
For a complete, real-world build, follow the worked example.
