# AI use cases for OpenDots (CopilotKit/OpenDots)

Repo: [CopilotKit/OpenDots](https://github.com/CopilotKit/OpenDots) | Use cases: 3 | Page: https://dedupedai.com/use-cases/copilotkit-opendots/

OpenDots is an open-source template from CopilotKit for persistent AI coworkers, each with its own computer, that move between web chat, mobile, Slack and calls. Agents can browse in an isolated browser, ask for human approval in chat, and keep working in the background. You host it yourself; conversations need CopilotKit Intelligence, either hosted, a local Docker evaluation, or a licensed self-hosted deployment.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Run your own always-on AI coworker app from a template: https://dedupedai.com/use-cases/copilotkit-opendots/run-the-opendots-template-locally/
- Approve what an agent does before it saves or sends: https://dedupedai.com/use-cases/copilotkit-opendots/approve-agent-actions-from-chat/
- Bring your OpenDots agent into Slack: https://dedupedai.com/use-cases/copilotkit-opendots/bring-your-agent-into-slack/

## How to run your own always-on AI coworker app from a template with OpenDots

Repo: [CopilotKit/OpenDots](https://github.com/CopilotKit/OpenDots) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README

Clone OpenDots, start the dev server, connect Intelligence and a model, and start chatting with a Dot.

**Who it is for:** A developer who wants a working base for an agent product with chat, pages and approvals.

**The problem:** Building persistent agents with computers, chat and approvals from zero takes months.

**The outcome:** OpenDots running at 127.0.0.1:5173 with Spaces, pages and Dots you can chat with.

### Steps

1. `git clone https://github.com/CopilotKit/OpenDots.git`, then `cd OpenDots` and `npm ci`
2. Run `cp .env.example .env` and `npm run dev`, then open http://127.0.0.1:5173
3. For hosted Intelligence run `npx copilotkit@latest login` and `npx copilotkit@latest project select`
4. Add OPENAI_API_KEY and OPENAI_MODEL to .env and restart; do not run copilotkit onboard in this folder

### Prompt to paste into your agent

```text
Set up CopilotKit/OpenDots locally with the local Docker Intelligence evaluation, add my model key from the environment, create one Dot for <role>, and confirm a chat works end to end.
```

### Caveat

With hosted Intelligence, conversation messages and tool calls are stored in CopilotKit's cloud.

Risk, credentials: The .env file holds your model key and Intelligence project key; keep it out of Git.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/copilotkit-opendots/run-the-opendots-template-locally/

## How to approve what an agent does before it saves or sends with OpenDots

Repo: [CopilotKit/OpenDots](https://github.com/CopilotKit/OpenDots) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Let a Dot browse in its isolated computer and pause on a human review card before acting.

**Who it is for:** A team that wants agents to do research and admin work, with a person signing off.

**The problem:** Fully autonomous agents can take actions nobody checked.

**The outcome:** Agent work that stops for your approval in chat, with a live view of its computer.

### Steps

1. Configure tool permissions for the Dot
2. Ask it for a task that needs browsing, for example find and save something
3. Watch the live computer view in chat
4. Approve or reject on the human review card

### Prompt to paste into your agent

```text
In CopilotKit/OpenDots, configure a Dot so every save or send needs my approval, then run <task> and show me the review card flow.
```

### Caveat



Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/copilotkit-opendots/approve-agent-actions-from-chat/

## How to bring your OpenDots agent into Slack with OpenDots

Repo: [CopilotKit/OpenDots](https://github.com/CopilotKit/OpenDots) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Connect Slack through the channels setup so the same agent answers there with shared threads.

**Who it is for:** A team that lives in Slack and wants its agent there too.

**The problem:** A separate agent web app is one more place nobody checks.

**The outcome:** The same Dot reachable from Slack and the web app.

### Steps

1. Get OpenDots running locally first
2. Follow the Setup docs for Slack
3. Mention the agent in a Slack channel and continue the thread on the web

### Prompt to paste into your agent

```text
Following CopilotKit/OpenDots' Setup docs, connect my Slack workspace to a Dot, list the Slack permissions it requests, and test one message round trip.
```

### Caveat



Risk, credentials: Slack app tokens grant workspace access; scope them narrowly.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/copilotkit-opendots/bring-your-agent-into-slack/