Deploy Your AI Agent to Any Channel — Website, Voice, Telegram, ChatGPT, Claude & CLI

Deploy Your AI Agent to Any Channel — Website, Voice, Telegram, ChatGPT, Claude & CLI

If you’ve just completed the Quick Start guide, welcome back. Your Claude Desktop, Claude Code, and ChatGPT Custom GPT are already set up. This guide picks up from there — covering all six deployment channels including website, voice, and Telegram, plus the setup steps for anyone arriving here fresh.

If this is your first stop, no problem. Everything you need is here from the beginning.

You now have an AI agent. Before we get into deploying it, let’s make sure you understand what that actually means — and then we’ll set it up together.

This is part of a Crash Course on Second Brain OS AI Agents. Access all the Automations to deploy your AI agent to 6 channels — website, voice, Telegram, ChatGPT, Claude & CLI — you get the full masterclass when you purchase ANY AI Agent by clicking the button below

Umair Kamil

Install Second Brain OS AI Agents

Who Is This Guide For?

You broadly fall into one of two categories:

Both paths are covered below. The setup steps are the same — only the channels you prioritise differ.

Getting Started: Set Up Your Second Brain OS Account

This guide covers everything — from initial setup to choosing your channels. If you’ve already completed the Quick Start guide, skip ahead to The Six Channels.

Step 1: Log In & Review Your Tools

1. Go to secondbrainos.com and log in
2. Navigate to My Actions — this is where all the MCP tools that came with your purchase are listed
3. Each tool has a visibility setting (public or private) and a status (active or inactive):
   • Public tools are available to your deployed agent across all customer-facing channels — your website chat widget, voice agent, Telegram bot, etc.
   • Private tools are hidden from your deployed agent entirely. These are setup-only tools used during configuration and are not available to customers on any channel.
4. By default, the core tools for your purchased product are already set to public and active. You can adjust these on a per-tool basis as needed

If you’re a business owner: Think of public vs private like front-of-house vs back-of-house. Public tools are what your customers interact with. Private tools are setup-only — they configure your agent behind the scenes and are never exposed to customers.

If you’ve used Zapier or n8n: Public = customer-facing automations. Private = setup-only, hidden from the deployed agent entirely.

Step 2: Connect Your External Services (If Applicable)

Depending on which AI agent you purchased, you may need to connect an external service (e.g. Calendly for appointment booking, a CRM for contact management, etc.).

If you purchased the Calendly AI Agent, follow the Calendly setup guide to connect your account before continuing.

The general process for Calendly & CRMs is:

1. Generate an API token or access key from the external service
2. In SBOS, click “Update CRM Settings” and paste the token in the appropriate field
3. Save — your external service is now connected and your AI agent can use it

If you’re a business owner: This is like giving your new hire the login credentials to your booking system. They need access to do their job — so does your AI agent.

If you’ve used Zapier or n8n: This is the same as adding a “connection” or “account” in Zapier. You authenticate once, and the platform uses those credentials for all future actions.

Step 3: Configure Your AI Agent Settings

Navigate to your Profile → AI Agent Settings. These settings control how your AI agent behaves across all channels:

• System prompt (auto_responder_instructions) — defines your AI agent’s personality, tone, and logic. Write it to match your business: a friendly virtual receptionist, a professional consultant, a knowledgeable sales assistant — whatever fits your brand
• LLM model (auto_responder_large_language_model) — the AI model your agent uses (e.g. gpt-5.4). Defaults to the latest available model
• OpenAI API key (open_ai_api_key) — required for ChatKit (website) deployments. Get yours at platform.openai.com/api-keys. Not required for voice, Telegram, Claude, or CLI deployments
• Domain — the domain where your ChatKit widget will live. Only required for ChatKit deployments
• Public domain key (domain_pk_xxx) — used by ChatKit to authenticate from the browser. Configure it at platform.openai.com/settings/organization/security/domain-allowlist. Only required for ChatKit deployments

Don’t have a system prompt yet? Use this starter template — copy it, fill in your details, and paste it into the auto_responder_instructions field:

Save your settings once configured.

If you’re a business owner: The system prompt is like the script you’d give a new receptionist. “Be warm and professional. Always confirm the appointment time.” The rest of the settings are one-time technical setup.

If you’ve used Zapier or n8n: The system prompt governs the AI’s entire personality and decision-making across all interactions — not just one workflow.

Step 4: Understand Your Tools

Your AI agent comes with a set of tools specific to what you purchased. A Calendly appointment booking agent includes tools to check availability, create meetings, reschedule, and cancel. A content creation agent includes tools to search knowledge, crawl websites, and publish content.

Each tool is called automatically during conversations — you don’t need to configure when or how they’re used. The AI decides based on the conversation.

To see what each tool does, visit My Actions in your SBOS dashboard.

Setup Complete — Now Choose Your Channels

Your Second Brain OS account is configured and your tools are ready. Everything from this point is about choosing where your customers will interact with your agent.

The Six Channels (+ CLI)

Here’s every way you can deploy your Second Brain OS agent:

Every channel connects to the same backend. Your tools, knowledge, and skills are shared across all of them.

Channel 1: Website Chat Widget (ChatKit)

This is the most common deployment. You add an AI-powered chat widget to your website where customers can have a conversation — ask about availability, book appointments, get answers from your knowledge base.

ChatKit is OpenAI’s embeddable chat component. Second Brain OS sits between ChatKit and OpenAI, injecting your tools and knowledge into every conversation. Your API keys never touch the browser — everything is validated server-side.

Two deployment options:

• Embed on existing site — add a script tag to your website header and a widget component to your page. Works on WordPress, Wix, Squarespace, Webflow, or plain HTML. For WordPress: paste the script into your header.php file and add the widget via a Custom HTML block on the page. For plain HTML: paste the script before the closing </body> tag.
• One-click Vercel deploy — for those without an existing website. Create a GitHub account, authorise Vercel, clone the provided template, update your domain key in index.html, commit the changes, and Vercel builds and deploys automatically with a free domain included.

Inline chat vs floating bubble:

• Inline chat — add the widget HTML to individual pages via a Custom HTML block (WordPress) or directly in your page HTML
• Floating bubble — add the script to your footer.php (WordPress) or before the closing </body> tag in your HTML. This makes the bubble appear on every page of your site

Read the full ChatKit deployment guide →

Channel 2: Voice AI (ElevenLabs)

Give your agent a voice. Customers call a phone number, speak to a natural-sounding AI receptionist, and book, reschedule, or cancel appointments — all by voice.

ElevenLabs handles the speech-to-text and text-to-speech. Second Brain OS connects via MCP, giving the voice agent access to the exact same tools your website chat uses.

What you configure:

1. Sign up to ElevenLabs. Go to Settings → Secrets — click Add Secret, name it “Second Brain OS”, enter Bearer [your SBOS API key] and save
2. Go to Developers → Environment Variables — add a new variable, select Secret type, choose the secret you just created and save
3. Go to Tools → Integrations → Add Integration → Custom MCP Server. Name it “Second Brain OS MCP”, select Streamable HTTP, enter your SBOS MCP URL from your dashboard setup link, click Add Header, name it “authorization”, select Environment Variable type, choose your SBOS variable, and save
4. In Tool Settings: set approval to No Approval, enable Post-Speech Execution, set Tool Call Sound to Typing, set Sound Behaviour to Always Play. Click “I trust this server” and add
5. Create a new blank agent — choose your voice (V3 Conversational recommended for natural feel). Set model to GPT 4.1, temperature to 0
6. Paste your system prompt from SBOS and add timezone variables at the top: {{timezone}}, {{utc_time}}, {{system_time}}
7. Go to Tools → MCP → Add MCP — attach your Second Brain OS MCP server to the agent

Read the full ElevenLabs deployment guide →

Channel 3: Telegram

If your customers are on Telegram, you can deploy your agent as a Telegram bot. The setup is straightforward — it follows the standard BotFather flow, and then you register the token with Second Brain OS.

Setup:

1. Open Telegram and message @BotFather
2. Send /newbot and follow the prompts to name your bot and get a bot token
3. Go to secondbrainos.com/telegram-integration
4. Paste your bot token and click “Install Telegram Integration”

Your Telegram bot is now connected to your Second Brain OS agent with all its tools, knowledge, and skills. Any tools set to public will be available. Any tools set to private will not.

Read the full Telegram deployment guide →

Channel 4: ChatGPT (Custom GPT)

If you or your customers already use ChatGPT, you can make your agent available as a Custom GPT. Custom GPTs use OpenAPI schemas to define tools (called “Actions”). Second Brain OS generates this schema for you automatically.

Setup:

1. Go to secondbrainos.com/open-ai-custom-gpts — copy your API key and download your schema file
2. Go to chatgpt.com → GPTs → Create → Configure
3. Upload a photo and name the GPT. Leave Description, Instructions, and Conversation starters empty for now
4. Click Create new Action → settings icon next to Authentication → API Key → Bearer — paste your API key and save
5. Open your schema file, select all, copy, paste into the Schema field, click Format
6. Add the privacy policy URL: https://secondbrainos.com/privacy-policy
7. Click Save → choose Only Me → open your Custom GPT and test it

Read the full Custom GPT deployment guide →

Channel 5: Claude Desktop

Claude natively supports MCP servers — one command connects your entire SBOS toolkit to Claude Desktop.

If you haven’t done the Quick Start:

1. Install Node.js from nodejs.org — the site highlights the right version for your machine
2. Install Claude Desktop from claude.ai/download. After installing, fully quit Claude before the next step
3. Go to secondbrainos.com/claude-model-context-protocol and copy your personal npx command
4. Paste it into your terminal and press Enter — it installs the MCP server and configures Claude automatically
5. When it says “Installation successful”, quit the terminal and reopen Claude Desktop
6. Click the + icon → Connectors → confirm Second Brain OS is listed. Go to Tool Access and select “Tools already loaded”. Go to Manage Connectors → Second Brain OS and click “Always allow” on all tools

Read the full Claude Desktop (MCP) deployment guide →

Channel 6: Claude Code (Terminal)

Claude Code brings your SBOS agent into the terminal. If you prefer working in the terminal — or want to script business operations alongside your agent — this is the most powerful option.

1. Install Homebrew if you don’t have it: go to brew.sh, copy the install command, paste into terminal and run. If prompted to set a path at the end, run that command too
2. Install prerequisites: brew install npm nvm node
3. Install Claude Code: brew install claude
4. Create a working folder: open Finder, press Cmd+Shift+G, type ~, create a folder (e.g. “My Second Brain OS”)
5. In terminal, navigate to it and start Claude Code:

   cd my-secondbrain-os
   claude

6. Press “Yes I trust this folder” when prompted
7. Type /mcp to verify Second Brain OS is connected. If not, open a new terminal tab and run your npx command from the SBOS dashboard first, then reconnect
8. Type /config and set thinking mode to false and model to Opus on low effort

Your agents and skills are available as slash commands — type / and search for them.

Read the full Claude Code deployment guide →

Channel 7: CLI / Agent URL (For Developers & Custom Integrations)

The Agent URL is a raw HTTP endpoint for your Second Brain OS agent. It accepts a POST request and returns a response — no UI, no framework, just your agent over HTTP.

Your agent endpoint:

Go to secondbrainos.com/agent-url to get your user-specific curl command:

curl -X POST 'https://openai.secondbrainos.com/completion' 
  -H 'Authorization: Bearer recXXX:xxx-xxx-xxx' 
  -H 'Content-Type: application/json' 
  -d '{
    "channel": "webchat",
    "conversation_id": "conv_123",
    "session_id": "webchat_visitor_JaneDoe",
    "deliver_to_webhook": false,
    "message": "What slots are available tomorrow?"
  }'

Key parameters:

What this unlocks:

• Custom chat UIs — build your own interface (React, Vue, mobile app) and hit this endpoint
• SaaS integrations — connect your agent to any platform that can make HTTP requests
• Agentic workflows — use session_id to maintain context across multiple calls and chain tasks
• Cross-platform continuity — a customer starts on WhatsApp, pick up the same session in your dashboard with full context
• Batch operations — process leads, check availability, and book appointments programmatically
• Claude Code integration — use curl within Claude Code to test and chain agent calls from your terminal

Read the full CLI & API deployment guide →

Which Channel Should You Start With?

If you’re a business owner deploying an AI receptionist:

• Start with ChatKit (website) — fastest way to get your agent live and test the booking flow visually
• Add ElevenLabs (voice) next — most customers still prefer calling, and voice has the highest conversion rate for appointment bookings
• Add Telegram if that’s where your audience is

If you’re a builder or developer:

• Start with Claude Desktop / Claude Code — test your agent’s tools interactively before deploying to customer-facing channels
• Use the CLI / Agent URL to build custom integrations and agentic workflows
• Deploy Custom GPT if your clients already use ChatGPT

The beauty of Second Brain OS is that you don’t have to choose. Configure once, deploy to all six. Each channel is independent — you can add or remove channels without affecting the others.

What’s Next

Pick a channel and follow its deployment guide:

• Website chat widget (ChatKit)
• Voice AI (ElevenLabs)
• Telegram
• ChatGPT Custom GPT
• Claude Desktop
• Claude Code
• CLI & Agent URL

This is part of a Crash Course on Second Brain OS AI Agents. Access all the Automations to deploy your AI agent to 6 channels — website, voice, Telegram, ChatGPT, Claude & CLI — you get the full masterclass when you purchase ANY AI Agent by clicking the button below

Umair Kamil

Install Second Brain OS AI Agents