Zendesk
Freshdesk
Gorgias
Front
Shopify
Stripe
Slack
Notion
Google Workspace
Confluence
Embedded Chatbot
Definition
An embedded chatbot is a Macha agent surfaced as a chat widget you embed — so the same agent you built and tested inside Macha can answer directly wherever you place it, with those conversations flowing back into history and evaluation.
How it works
You build and test an agent in Macha exactly as you would any other — instructions, tools, data sources — and expose it as an embeddable chat surface. It's the same agent, so it grounds answers in the data sources you attached and respects the tool access you granted; a customer-facing embed typically leans on read tools and knowledge rather than unconfirmed writes.
Embedded chatbot conversations are first-class: they show up in the agent's history and are graded by Agent Evaluation alongside chat sessions, autonomous runs, and sub-agent handoffs, so you can measure how the widget is performing just like everything else.
Why it matters
Because the embed is a real Macha agent, you're not maintaining a separate bot with separate rules. The same knowledge sources, the same instructions, and the same evaluation loop apply — build once, and deploy the agent in the dashboard and as a widget.
Frequently asked
Is the embedded chatbot a different product from my agents?
No. It's one of your Macha agents presented as a chat widget. Same instructions, same tools, same data sources — just a different surface.
Do embed conversations show up in evaluation?
Yes. Embedded chatbot conversations are captured in the agent's history and are scored by Agent Evaluation just like chat and autonomous runs.
Related terms
Data Sources
Data sources (also called knowledge sources) are the knowledge an agent reads from — uploaded documents, indexed websites, and live content from connected apps like Google Docs, Notion, and Confluence.
Agent Evaluation
Agent Evaluation is Macha's built-in way to score how well an agent actually did its job.
AI Copilot
An AI copilot is an assistant that works alongside a human — suggesting replies, summarizing context, and surfacing information — while the person stays in control and makes the final decision, rather than acting autonomously..
Conversational AI
Conversational AI is technology that lets people interact with software through natural back-and-forth dialogue — understanding intent, maintaining context across turns, and responding in natural language via chat or voice..
Put these ideas to work
Macha is an AI agent layer that sits on top of the help desk you already run — Zendesk, Freshdesk, Front, Intercom, or Gorgias.
Start Trial