> For the complete documentation index, see [llms.txt](https://docs.dapta.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.dapta.ai/ai-text-agents/dapta-and-whatsapp/dapta-agent-vs-meta-business-agent.md). # Your Dapta agent and Meta's Business Agent WhatsApp Business has its own AI assistant. What it is, how it differs from a Dapta Text Agent, and why Dapta's onboarding asks you to turn it off. WhatsApp Business now has an AI assistant of its own, built by Meta. If you have seen it in the app, this page explains what it is, how it relates to Dapta, and how to choose. ## They are two different products | | Meta Business Agent | Dapta Text Agent | | -------------- | ------------------------ | ----------------------------------------- | | Built by | Meta | Dapta | | Where it lives | Inside WhatsApp Business | In Dapta, answering on your WhatsApp line | | Turned on by | You, in Meta's tools | You, by assigning the agent to a line | | Billed by | Meta | Dapta, for the agent; Meta, for delivery | **Connecting your line to Dapta does not switch Meta's assistant on, and using Dapta does not require it.** They are separate things that happen to work on the same number — which is exactly why only one of them should be answering. {% hint style="warning" %} **One number, one AI.** If Meta's assistant is enabled on a number you want Dapta to answer on, turn it off before you connect. Dapta's onboarding requires it. Your team can still reply by hand from the WhatsApp Business app exactly as before — that is a person writing, not an AI. {% endhint %} *** ## Where each one fits Meta's assistant is built into WhatsApp and needs very little setup. If what you need is a greeting, your opening hours, and answers to a handful of common questions, it is right there and it will do that. A Dapta Text Agent is built for what comes after the first answer: knowing your real inventory, doing something in your systems, recording the result, reaching out first, and involving a person at the right moment. | What you need | Meta Business Agent | Dapta Text Agent | | ------------------------------------------------ | ----------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Greet, give hours, answer FAQs** | Yes | Yes | | **Answer from your catalogue, files or website** | From what you can load into Meta's tools | [Brains](/ai-text-agents/setting-up-your-text-agent/brains-for-text-agents.md) built from your own sources | | **Reach into your systems** | Possible — Meta's platform can call external APIs, with technical setup | [Actions](/ai-text-agents/setting-up-your-text-agent/text-agent-actions.md) plus ready-made connections like [CRM Pipeline Sync](/ai-text-agents/setting-up-your-text-agent/crm-pipeline-sync.md) and calendar booking | | **Record what each conversation produced** | Read the chat | [Post-conversation analysis](/ai-text-agents/setting-up-your-text-agent/post-conversation-analysis.md) extracts the fields you define | | **Start conversations with a list of contacts** | Not the same workflow | [Sequences](/ai-text-agents/campaigns.md): import, schedule, retry, fall back to a call | | **Protect the line while you send at volume** | Not offered as a campaign feature | [Line protection](/ai-text-agents/campaigns/message-logic-and-limits.md): quality monitoring, send limits, automatic pauses | | **A team operating one number together** | Limited to the app | [Inbox](/ai-text-agents/inbox.md): assign, take over, release, tag, filter | | **The same agent on your website** | Not available | The [widget](/ai-text-agents/channels/widget-embed-your-text-agent-on-a-website.md), into the same Inbox | | **Choose the model and test before going live** | Not available | A model per agent, and the [Playground](/ai-text-agents/setting-up-your-text-agent/playground-testing-your-text-ai-agents.md) | | **Report on it** | Meta's own numbers | [Metrics, history and exports](/ai-text-agents/analytics-and-logs.md) | {% hint style="info" %} **Being fair about it.** Meta's platform *can* connect to external systems and *can* hand a conversation to a person — anyone telling you otherwise is wrong. The honest difference is how much work it takes to get a working result, and whether outbound campaigns are part of the picture at all. {% endhint %} *** ## How to choose **Meta's assistant is probably enough if** your WhatsApp is mostly people asking the same few questions, you answer them yourself today, and you are not sending campaigns. **A Dapta Text Agent earns its place when** any of these is true: * You want to **start** conversations, not only answer them — campaigns, reminders, re-engagement. * The answer depends on something only your systems know: stock, an order, an appointment, a price for this customer. * The conversation should **do** something afterwards: move a deal, create a record, book a slot. * More than one person works the number and you need to see who is handling what. * You want the same agent on your website, with everything in one place. Some customers who had been using Meta's assistant and moved to Dapta have told our team they preferred the quality of Dapta's answers. That is early feedback from a handful of businesses rather than a measured benchmark — the honest test is your own: set both up against the same questions and compare. *** ## What to do next {% content-ref url="/pages/8yBxnycfBbLwmHztlM7I" %} [Prepare your Meta account](/ai-text-agents/channels/prepare-your-meta-account.md) {% endcontent-ref %} {% content-ref url="/pages/TXgOhDoCH3jfppJaD1K2" %} [Dapta and WhatsApp Business](/ai-text-agents/dapta-and-whatsapp.md) {% endcontent-ref %} {% content-ref url="/pages/Fos4bKY11uC0JD7tNfmx" %} [What people use Text Agents for](/ai-text-agents/use-cases.md) {% endcontent-ref %} --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.dapta.ai/ai-text-agents/dapta-and-whatsapp/dapta-agent-vs-meta-business-agent.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.