> For the complete documentation index, see [llms.txt](https://docs.360dialog.com/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.360dialog.com/docs/mba/meta-business-agent/faq.md).

# FAQ

Answers to the questions we hear most while clients integrate Meta Business Agent (MBA). For anything not covered here, check [Known limitations & workarounds](https://docs.360dialog.com/docs/mba/meta-business-agent/known-limitations.md) or reach out to your 360dialog contact.

## Getting started

<details>

<summary>Do I need a credit line to try MBA?</summary>

**No — not to test it.** You can complete eligibility, enable, configure, test, and go live on an **allowlist** (`ALLOWLISTED_ONLY`) without any payment method on file. A payment method is only required before you switch the agent to answer **everyone** (`EVERYONE`). See [Roll out to everyone](https://docs.360dialog.com/docs/mba/meta-business-agent/6.-roll-out-to-everyone.md).

</details>

<details>

<summary>What payment methods are supported?</summary>

A **direct credit line** with Meta, managed via Billing Hub. **Credit-card payment** has been rolling out gradually since September 2026 — check Billing Hub to see whether it's available for your account.

</details>

<details>

<summary>Can I use 360dialog's (or my partner's) credit line for a client's MBA?</summary>

**No.** A credit line belongs to the **Business Manager that owns the WABA**, and MBA billing follows that same rule — a 360dialog or tech-provider credit line can't be reused for an end client's agent, even if that credit line is already attached to the WABA for other purposes. Each client needs to add or apply for **their own** credit line.

</details>

<details>

<summary>My client's Business Portfolio doesn't even show an option to apply for a credit line — what can they do?</summary>

Check whether card payment is available for the account in Billing Hub, or have the client check their eligibility directly on Meta's **Payment Methods** page in Business Manager — 360dialog can't apply for a credit line on a client's behalf.

</details>

<details>

<summary>How is MBA billed?</summary>

Usage is **postpaid**: charged at the start of the following month. There's no prepayment and no mid-month charge. If you're on a credit line and utilization hits **100%**, MBA access is **suspended** until it's resolved — a [usage budget](https://docs.360dialog.com/docs/mba/meta-business-agent/controlling-your-agent.md#usage-budget) is the practical way to avoid hitting that ceiling unexpectedly.

</details>

<details>

<summary>Does MBA usage show up in my normal WhatsApp billing analytics?</summary>

**No.** MBA usage doesn't appear in the standard WhatsApp message billing analytics. Track usage and cost with the usage insights endpoint (see [Track usage and spend](https://docs.360dialog.com/docs/mba/meta-business-agent/controlling-your-agent.md#track-usage-and-spend)), and cap it with a [usage budget](https://docs.360dialog.com/docs/mba/meta-business-agent/controlling-your-agent.md#usage-budget).

</details>

<details>

<summary>Does the pricing change coming 1 October 2026 affect MBA?</summary>

**No — MBA pricing itself doesn't change.** The 1 October update is about **service messages sent by anything other than MBA** (a human agent, or your own 3rd-party AI/backend) — those start being billed per message from that date, with one exception: the **first 1,000 service messages per phone number per month are free**. That free allowance applies to non-MBA service messages, not to MBA messages, and it counts per message, not per conversation.

MBA messages have been billed separately since 1 August 2026, at a flat rate of **$2.00 per 1 million tokens (roughly 4–5 US cents per message)**, covering message delivery and AI processing in a single charge. Nothing about that rate or mechanism changes on 1 October.

</details>

<details>

<summary>How do I onboard — API, or something more hands-off?</summary>

Four ways, depending on how much control you want:

* **360dialog MCP** — connect your AI assistant (Claude, Cursor, Codex…) to the 360dialog MCP and set up the agent by describing what you want. The simplest option, and great for drafting the agent's knowledge and skills.
* **Via API** — build your own onboarding and management experience. Full control. This guide covers that path.
* **MBA Integrated Onboarding** — a hosted, guided flow (similar to 360dialog's Number Integrated Onboarding) that handles terms acceptance and setup for you.
* **360dialog Hub** — enable and manage MBA directly from the Hub UI, no integration work at all.

See [Onboarding options](https://docs.360dialog.com/docs/mba/meta-business-agent/onboarding-options.md).

</details>

<details>

<summary>Is MBA available for my number?</summary>

It depends on eligibility (vertical, account standing, and a few other factors) — run the eligibility check before assuming. If the number isn't eligible, the response includes an `ineligibility_reason` you can show the client. See [1. Check eligibility](https://docs.360dialog.com/docs/mba/meta-business-agent/1.-check-eligibility.md).

</details>

<details>

<summary>Can I use MBA on Instagram?</summary>

**Not through 360dialog today.** Meta is adding Instagram support for approved integrations, but 360dialog's MBA integration covers WhatsApp. Set up and configure the agent for WhatsApp as usual.

</details>

## Testing

<details>

<summary>Can I test MBA before opening it to real customers?</summary>

Yes. Use [`agent_test`](https://docs.360dialog.com/docs/mba/meta-business-agent/4.-test-your-agent.md) right after configuring — no need to switch to `EVERYONE`. Then add your own numbers to the **allowlist**, set `ai_audience` to `ALLOWLISTED_ONLY`, and message the agent from those numbers on real WhatsApp. See [5. Go live](https://docs.360dialog.com/docs/mba/meta-business-agent/5.-go-live.md).

</details>

<details>

<summary>Does the <code>agent_test</code> endpoint work during allowlist testing?</summary>

**Yes.** `agent_test` returns real replies before go-live and while the agent runs under `ALLOWLISTED_ONLY`. Each call starts a fresh conversation unless you pass back a `conversation_id`. See [4. Test your Agent](https://docs.360dialog.com/docs/mba/meta-business-agent/4.-test-your-agent.md).

</details>

<details>

<summary>How do I see why the agent replied the way it did?</summary>

Pull that conversation's **turns** — each one shows the internal steps the agent took (which tool it called, what it returned, how long each step took, and whether anything errored or timed out). It also works for `agent_test` conversations: pass the test's `conversation_id`. See [Conversation turns](https://docs.360dialog.com/docs/mba/meta-business-agent/controlling-your-agent.md#conversation-turns).

</details>

## Configuration

<details>

<summary>What can I actually teach the agent?</summary>

Three things: **knowledge** (business info, FAQs, files, websites it can reference), **behavior** (skills — your workflows and tone, written as natural-language directives), and **capabilities** (connectors and tools that call your own APIs, plus interactive messages for rich WhatsApp components). See [3. Configure your agent](https://docs.360dialog.com/docs/mba/meta-business-agent/3.-configure-your-agent.md).

</details>

<details>

<summary>I created a skill and got 201, but the agent ignores it. Why?</summary>

Check the skill's `status`. Every skill goes through an automated content review, and a `blocked` skill is saved but never applied — most often because it asks for or mentions sensitive personal data such as date of birth or ID numbers. Edit it to remove that content and the review runs again. See [Skills](https://docs.360dialog.com/docs/mba/meta-business-agent/3.-configure-your-agent.md#skills).

</details>

<details>

<summary>Can I upload a spreadsheet or a PDF with a table as a knowledge source?</summary>

Not reliably today. **CSV files, and tables inside PDFs, error out** when the agent tries to read them. Put structured or tabular facts into FAQs or business info instead. See [Known limitations](https://docs.360dialog.com/docs/mba/meta-business-agent/known-limitations.md#files).

</details>

<details>

<summary>Can the agent read files or videos customers send?</summary>

Images (with their caption) and voice notes (as a transcript) yes. Videos, documents such as PDFs or Office files, and other audio files no — the agent is told it got something it can't read, so it can ask for another format. Upload documents the agent should know as [knowledge files](https://docs.360dialog.com/docs/mba/meta-business-agent/3.-configure-your-agent.md#files).

</details>

<details>

<summary>Can the agent send a file, image or video back to a customer?</summary>

Yes. Sending **rich messages** (images, videos, buttons, carousels, lists, locations, flows) via [interactive messages](https://docs.360dialog.com/docs/mba/meta-business-agent/3.-configure-your-agent.md#interactive-messages-ui-skills) is supported and is the right tool for that.

</details>

<details>

<summary>What's the difference between a regular Skill and a UI Skill?</summary>

A regular **Skill** (Meta now calls these *agent instructions*) tells the agent how to think and respond — tone, priorities, workflows, all in plain text. A **UI Skill** (Meta now calls these *interactive messages*) tells it *when* to reply with a rich WhatsApp component instead — a button, image, video, list, carousel, location, or Flow — again as a natural-language instruction rather than a JSON payload you build yourself. See [Interactive messages](https://docs.360dialog.com/docs/mba/meta-business-agent/3.-configure-your-agent.md#interactive-messages-ui-skills).

</details>

<details>

<summary>Can I connect the agent to my own systems (order lookup, booking, inventory)?</summary>

Yes, via **Connectors and tools** — you define an external API once (a Connector), then add individual operations on it (Connector Tools) with a clear description so the agent knows when and how to call them. See [Connectors and tools](https://docs.360dialog.com/docs/mba/meta-business-agent/3.-configure-your-agent.md#connectors-and-tools).

</details>

<details>

<summary>Can I connect an MCP server as a connector?</summary>

**Not yet.** MCP-based connectors are on Meta's roadmap but not shipped. Integrate via the REST connector + tool model for now. See [Known limitations](https://docs.360dialog.com/docs/mba/meta-business-agent/known-limitations.md#connectors).

This is different from the **360dialog MCP**, which you connect to your own AI assistant to set up and manage the agent. See [Onboarding options](https://docs.360dialog.com/docs/mba/meta-business-agent/onboarding-options.md).

</details>

<details>

<summary>Can I cap how much the agent spends?</summary>

Yes — set a **usage budget**, capping token or AI-turn usage within a rolling time window (one day up to thirty days), or within a fixed campaign period with `start_date` and `end_date`. Once the cap is hit, the agent stops responding until the window resets. See [Usage budget](https://docs.360dialog.com/docs/mba/meta-business-agent/controlling-your-agent.md#usage-budget).

</details>

<details>

<summary>Can I make the agent send a specific, exact-match message at a certain point (e.g. for conversion tracking)?</summary>

You can instruct it to — write a skill telling the agent to reply with an exact phrase when a specific condition is met (e.g. "once the booking is confirmed, reply with exactly: '...'"). In our own testing this behaves as expected, but treat it the way you would any AI-generated output: it's a strong instruction, not a hard guarantee of byte-for-byte output every time. If you're wiring this into an exact-match tracking system (e.g. a conversion tool that matches on literal text), monitor it after launch rather than assuming it'll never drift.

</details>

## Handoff & control

<details>

<summary>What happens when the agent hands off to a human?</summary>

It **stops answering that chat** entirely — make sure a human handover path is actually staffed before you launch, or those customers get silence. On hand-back, the agent also **loses the earlier conversation context**, so don't assume continuity across a handoff. See [Configure your agent — Handoff](https://docs.360dialog.com/docs/mba/meta-business-agent/3.-configure-your-agent.md#handoff).

</details>

<details>

<summary>Can I take over a conversation the agent is handling, and give it back?</summary>

Yes. You take control implicitly the moment you send a message to that conversation — from then on, the consumer's messages arrive on `messages` instead of `standby`, and the agent stays quiet. Hand it back with the Thread Control endpoint: `pass` with `target_role: "ai_agent"` gives it straight to the agent, and `release` returns it to idle so the customer's next message goes to the primary responder. There's no endpoint to *read* who currently holds a conversation — infer it from the `standby` vs `messages` routing and `messaging_handovers` events. See [Thread control](https://docs.360dialog.com/docs/mba/meta-business-agent/controlling-your-agent.md#thread-control).

</details>

<details>

<summary>Does the agent always reply in the customer's language?</summary>

Not always automatically — reinforce language behavior explicitly in your skills where it matters.

</details>

<details>

<summary>Can I A/B test MBA against my existing WhatsApp flow on the same number?</summary>

Yes, but it's not a built-in percentage-split toggle — you build the split into your own routing. The pattern: keep your existing flow as the default, and only **pass thread control to MBA** (`pass` with `target_role: "ai_agent"`) for the subset of conversations you want in the test (for example, a random split at the point a user enters a specific journey). MBA doesn't take over a conversation until thread control is passed to it, so whatever owns your routing logic upstream — your flow builder, your backend — decides which users get the MBA-led experience. See [Thread control](https://docs.360dialog.com/docs/mba/meta-business-agent/controlling-your-agent.md#thread-control).

</details>

## Known limitations & open questions

<details>

<summary>Is the platform stable enough for production traffic?</summary>

MBA is still in early access, but errors are much clearer than at launch: most failures now return a specific `400`, `403`, `404` or `409` that tells you what to fix. Only retry `429` and `500` later. See [Known limitations — Errors and retries](https://docs.360dialog.com/docs/mba/meta-business-agent/known-limitations.md#errors-and-retries).

</details>

<details>

<summary>Is billing fully finalized?</summary>

Not entirely. The payment-method mechanics above are confirmed, and usage and cost are available through the [usage insights endpoint](https://docs.360dialog.com/docs/mba/meta-business-agent/controlling-your-agent.md#track-usage-and-spend), but MBA usage still isn't in standard billing analytics. Treat commercial terms as provisional and check [Known limitations](https://docs.360dialog.com/docs/mba/meta-business-agent/known-limitations.md#billing) for the latest.

</details>

<details>

<summary>Can I read who currently owns a conversation via the API?</summary>

No. There's no endpoint that returns the current owner. Infer ownership from the `standby` vs `messages` routing and `messaging_handovers` events. See [Thread control](https://docs.360dialog.com/docs/mba/meta-business-agent/controlling-your-agent.md#thread-control).

</details>

<details>

<summary>What's still coming that isn't documented yet?</summary>

* **MCP-based connectors** — on Meta's roadmap, no date yet.

We'll fold this into the relevant page as soon as it ships — this FAQ and [Known limitations](https://docs.360dialog.com/docs/mba/meta-business-agent/known-limitations.md) are the two pages to check back on.

</details>


---

# 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.360dialog.com/docs/mba/meta-business-agent/faq.md?ask=<question>&goal=<user_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.
