How Do You Deploy an AI Chatbot on Your Website with Macha? (Step by Step)

You deploy an AI chatbot on your website with Macha in three steps: pick one of your agents to power it, style the widget (header, greeting, avatar, colour, position, allowed domains), and paste a single <script> tag into your site's <head>.

Because the chatbot is a real agent in a widget, it answers from your knowledge sources, can look things up with the agent's tools, and escalates to a human when it can't help. The whole install takes minutes; the testing afterwards is where the time goes.

What is a Macha chatbot?

A Macha chatbot is a public, customer-facing widget you embed on your website or help center. It's powered by one of your agents, so it inherits that agent's instructions, knowledge sources and tools. Whatever the agent can do in Macha, the chatbot can do for your visitors: answer from your help center, look up an order, check a subscription, grounded in your real content rather than a generic model.

That's the difference between a scripted website bot and this one: a scripted bot follows a decision tree; a Macha chatbot reasons over your knowledge and acts. When it can't help, it opens a ticket in your help desk with the full conversation attached. (For the deflect-vs-resolve angle specifically, see how to add a Zendesk AI chatbot that resolves.)

What do you need before you start?

• An agent to power it. If you haven't built one yet, do that first and give it the knowledge and tools you want the chatbot to use. (See what a Macha agent is.) A "Support" agent grounded in your help center is the usual choice.
• A Macha account. Website chatbots are included in Macha's one plan, and the trial ($50 of free usage, no credit card) is enough to deploy and test one.
• Access to your site's HTML (or your CMS or site builder) to paste one line of code.

How does the three-step setup work?

Everything below fits in three moves: pick an agent → configure the widget → embed it. The Chatbots page lays it out exactly this way.

Step 1: Create a chatbot and pick its agent

Go to Chatbots and click Create Chatbot. Give it a name (internal; your visitors won't see it) and choose the agent that will power it. This is the single most important choice: the agent's knowledge and tools are the chatbot's brain. Point it at a support agent grounded in your help center and the chatbot answers from your real content.

Step 2: Configure the widget

This is where you make it look and behave the way you want. As you change settings, the live preview on the right updates so you can see exactly what visitors will get.

• Header title: the text at the top of the chat panel (for example, "Chat with us").
• Greeting: the first message visitors see (for example, "Hi! What can I help with today?").
• Avatar: upload an image to brand the bot.
• Primary colour: match your brand; it tints the header and launcher.
• Position: anchor the launcher to a corner. You set Top / Right / Bottom / Left independently (in px, em or rem). Fill the two sides you want and leave the opposite pair blank. Bottom-right is the convention.
• Allowed domains: restrict the widget to load only on domains you own, so nobody can lift your embed code onto another site.
• Tool safety (read-only vs. write): the chatbot inherits the agent's tools, but write actions such as refund, cancel or update are off by default until you switch them on. On a public widget, enabled write actions execute without a confirmation step, so start read-only and open up specific write tools only when you trust the setup.

Step 3: Embed it on your site

When you're happy, Macha gives you a single line of code: a <script> tag tied to this chatbot. Paste it into your site's <head> (or your CMS's "custom code" or "footer scripts" area), publish, and a floating launcher appears in the corner.

That's the whole install. A few things happen automatically once it's live:

• Visitor sessions persist across page loads (via localStorage), so a returning visitor keeps their conversation.
• Every conversation shows up in your Macha dashboard, so you can review what visitors asked and how the bot answered.
• Rate limits apply per session, per IP and per domain, plus a hard cap on conversations per day, so a traffic spike can't quietly drain your usage.

Step 4: Test it before you point traffic at it

Open your site, click the launcher, and run it through the questions you actually get:

• Ask a common FAQ. Does it answer from your help center accurately?
• Ask something it shouldn't answer. Does it decline or escalate cleanly instead of guessing?
• If you enabled an action (like an order lookup), test it with real-ish data.

Watch the first batch of real conversations in the dashboard and tighten the agent's instructions or knowledge based on what you see. The chatbot is only as good as the agent behind it, so most tuning happens on the agent, not the widget. A change to the agent's instructions reaches the chatbot on the next message.

Which chatbot settings can you customize?

Where should you put your chatbot, and which agent should power it?

The same widget behaves very differently depending on where it lives, so match the agent and the placement to the page:

• Help center / docs: a support agent grounded in your articles. This is the highest-value spot: visitors are already trying to self-serve, and the bot can resolve them before they ever file a ticket.
• Homepage and product pages: a pre-sales agent that answers "does it do X?" and points to the right page. With Cal.com connected, it can propose times and book a demo.
• Pricing / checkout: answers plan and billing questions at the moment of highest intent, where a stuck visitor often means a lost sale.
• Inside your app: a support agent scoped to account-aware tools, for logged-in users.

You can run a different chatbot, powered by a different agent, on each surface, so the docs bot, the pre-sales bot and the in-app bot can each be tuned for their job.

How do you build a support chatbot in under 10 minutes?

Say you want a help-center bot that deflects common questions:

1. Build a Support agent. Instructions: "Answer support questions from the help center. If you're not confident, or the request needs account access, tell the visitor you'll connect them to the team." Knowledge: your Zendesk Help Center, added as an indexed knowledge source. Tools: read-only.
2. Create a chatbot and pick that agent.
3. Style it: header "Need help?", greeting "Ask me anything about [product]", your brand colour, anchored bottom-right.
4. Lock allowed domains to your docs domain only.
5. Embed the one-line script in your help center's <head> and publish.
6. Test five real questions, then watch the first transcripts and refine the agent's instructions.

Ten minutes of work, and self-serve questions get answered instantly instead of turning into tickets, while the ones the bot can't handle escalate cleanly with context.

What keeps a website chatbot accurate and safe?

• Ground the agent well. Keep its help center and knowledge current; that's where answer quality comes from. Indexed sources such as websites need a manual Resync after you update the content.
• Start read-only. Add write actions only once you trust the answers.
• Set a clear greeting that tells visitors what the bot can help with, and make escalation to a human easy.
• Lock the allowed domains so your embed can't be reused elsewhere.
• Review transcripts weekly for the first month and refine the agent.

Frequently asked questions

How long does it take to deploy a Macha chatbot? Minutes. Pick an agent, configure the widget, and paste one line of code.

What powers the chatbot's answers? An agent you choose. It uses that agent's knowledge sources and tools, so answers come from your real content, not a generic model.

Where do I paste the embed code? Into your site's <head>, or the "custom code" or "footer scripts" section of your CMS or site builder.

Can I limit where the chatbot appears? Yes. Set allowed domains so the widget only loads on sites you own.

Can the chatbot take actions, not just answer? Yes, if you enable write tools, which are off by default. On a public widget they run without a confirmation step, so scope them carefully and start read-only.

Which plans include chatbots? Macha has one plan, and chatbots are included in it; there is no separate per-chatbot price.

How is a chatbot conversation billed? As one ticket, however many messages it takes. Macha's plan is priced by monthly ticket volume, starting at $299 a month for up to 750 tickets, and a ticket runs up to 50 messages under fair use.

Deploy your first chatbot: pick an agent, style it, and embed it in minutes. $50 of free usage, no credit card required. Start free.