How do I keep track of what an account posts on X (Twitter) with AI?
Connect SocialToAI to your AI client over MCP, then ask in plain words. In this recorded run an AI client answered “What did NASA post on X this week, and which posts took off?” with 1 request on X: 21 items read in 5.5 seconds for 9 credits ($0.03). 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.
The question
What did NASA post on X this week, and which posts took off?
An account's timeline shows posts newest first, and whether a post did well depends on that account's usual numbers, which you would have to work out yourself. Reading what this run returned by hand takes about 3 minutes (600 words at 240 a minute).
What the AI did
It chose the tools itself: 1 request on X. 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 |
|---|---|---|---|---|---|
| X | account_watch | accounts: ["https://x.com/NASA"] · window: "7d" · scale: "small" | 1 | 21 posts | 9 |
| Total | 1 | 21 items | 9 | ||
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.
20 posts in the window; the account's usual is 1,436 interactions a post. What stands out:
- Posts that took off (2× the usual or more)20%“While observing the universe, @… caught a galaxy cluster smiling for the camera. 😊 The sm”4 posts
- News80%4 of the 5 posts analysed4 posts
- Promotion20%1 of the 5 posts analysed1 post
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.
- X · post7dFinding 1
While observing the universe, @… caught a galaxy cluster smiling for the camera. 😊 The smile lines are arcs caused by an effect known as gr
Open the source
What it cost
1 request, 9 credits in total: $0.03 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 | $0.03 |
| $50 = 20,000 credits | 400 | $0.022 |
| $200 = 100,000 credits | 500 | $0.018 |
Ask it yourself
Connect SocialToAI to your AI client once (the steps for each client), then paste the question. You do not name tools or parameters: the client picks them.
What did NASA post on X this week, and which posts took off?The same in code: the calls this run made, as requests to the API.
curl https://api.socialtoai.com/v1/tools/account_watch \ -H "Authorization: Bearer $SOCIALTOAI_KEY" \ -H "Content-Type: application/json" \ -d '{ "accounts": ["https://x.com/NASA"], "window": "7d", "scale": "small" }'What to try next
- Ask next: “Why did the top post take off?”
- Ask next: “Watch two more accounts”
- Add two competitors' accounts.
- Set it to run every week.
- Run it as one request with the ready-made tool Account watch: What a set of accounts published lately and which posts did clearly better than each account's usual.
Last updated: