# How do I track which of an account's TikTok videos took off with AI?

Connect SocialToAI to your AI client over MCP, then ask in plain words. In this recorded run an AI client answered “Which of NASA's TikTok videos took off this month?” with 1 request on TikTok: 21 items read in 9.3 seconds for 12 credits ($0.04). Below are the calls it made, the answer with its sources, and the prompt and API calls to run it yourself. Recorded 2026-10-18.

- Page: https://socialtoai.com/docs/guides/monitor-an-account-on-tiktok/
- Last updated: 2026-10-18

## The question

> Which of NASA's TikTok videos took off this month?

A profile lists videos with their views, but not how far each is from the account's usual, which is what tells a breakout from a normal week. Reading what this run returned by hand takes about 2 minutes (549 words at 240 a minute).

## What the AI did

It chose the tools itself: 1 request on TikTok. Each row is one tool call as the client showed it, with what it sent, how much came back and what it cost.

| Platform | Tool | Sent | Requests | Returned | Credits |
| --- | --- | --- | --- | --- | --- |
| TikTok | [`account_watch`](https://socialtoai.com/tools/account-watch.md) | `accounts: ["https://www.tiktok.com/@nasa"] · window: "30d" · scale: "small"` | 1 | 21 videos | 12 |
| **Total** |  |  | 1 | 21 items | **12** |

## The answer

What the client answered, from what it had read. The line under each finding is a post it read, or a figure from those posts.

Recorded 2026-10-18

12 posts in the window; the account's usual is 14,975 interactions a post. What stands out:

1. **Posts that took off (2× the usual or more)** (33%, 4 videos): [“Suited up. Next stop: the International Space Station. 🚀 Crew-13 is targeting liftoff tod”](https://www.tiktok.com/@nasa/video/7691683140015820046)
2. **News** (80%, 4 videos): 4 of the 5 posts analysed
3. **Promotion** (20%, 1 video): 1 of the 5 posts analysed

Used 12 credits · $0.04. Every claim links to its source.

### The posts it rests on

A selection of what was read; the marked words are what a finding rests on. An item without a link says so.

- TikTok · video · 2w: “Suited up. Next stop: the International Space Station. 🚀 Crew-13 is targeting liftoff today at 11:10 a.m. EDT! Watch coverage starting at 9” ([Open the source](https://www.tiktok.com/@nasa/video/7691683140015820046))

## What it cost

1 request, 12 credits in total: $0.04 at the $10 rate. Every answer of the API states the credits it charged and the balance left, so your AI can tell you what a question cost. A call that fails costs nothing.

| Pack | Credits per dollar | This answer |
| --- | --- | --- |
| $10 = 3,000 credits | 300 | $0.04 |
| $50 = 20,000 credits | 400 | $0.03 |
| $200 = 100,000 credits | 500 | $0.024 |

## Ask it yourself

Connect SocialToAI to your AI client once ([the steps for each client](https://socialtoai.com/mcp.md)), then paste the question. You do not name tools or parameters: the client picks them.

**Prompt**

```
Which of NASA's TikTok videos took off this month?
```

The same in code: the calls this run made, as requests to the API.

**tool.account_watch**

```
curl https://api.socialtoai.com/v1/tools/account_watch \
  -H "Authorization: Bearer $SOCIALTOAI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "accounts": ["https://www.tiktok.com/@nasa"],
    "window": "30d",
    "scale": "small"
  }'
```

## What to try next

- Ask next: “Why did the top post take off?”
- Ask next: “Watch two more accounts”
- Ask it to read the comments under the top video.
- Add more accounts and compare.
- Run it as one request with the ready-made tool [Account watch](https://socialtoai.com/tools/account-watch.md): What a set of accounts published lately and which posts did clearly better than each account's usual.

- [TikTok MCP server](https://socialtoai.com/mcp/tiktok.md): What your AI can read on TikTok, and how to connect it.
- [TikTok API](https://socialtoai.com/platforms/tiktok.md): Every call on TikTok, with its credits and a request you can copy.