Use case · TikTok

See the stats of any TikTok account with your AI

One question to ChatGPT or Claude: average views, engagement rate, posting rhythm and best videos of any account. No need to own it.

Connect your AI · 1-minute setup · $2 free

How do you see TikTok analytics for any account?

Read the account’s public numbers: followers, then its last few dozen posts with views, likes, comments, shares and dates. From those you get average and median views, engagement rate, posts per week and the formats that win. With Whizbrew connected, ChatGPT or Claude does all of it from one question, in about a minute.

Key takeaways

  1. Duolingo’s typical post does 718K views, but the average is 1.74M: its top 5 posts bring 43% of all views, and a 5M+ hit lands about every 11 days.
  2. Engagement is huge: likes, comments and shares add up to 18.4% of views. Brand tie-ins (Taco Bell, NYFW) get 6.9%.
  3. It posts 6.4 times a week, almost only on weekdays (58 of 60 posts), and its artist-made animations do 2.25M median, 3× the rest of the feed.

The question to ask your AI

How is @duolingo doing on TikTok? Read its profile and its last 60 posts: average and median views, engagement rate, how often and on which days it posts, and which formats beat its usual. Show me the best videos and finish with what I should copy for my own account.

What your AI does, step by step

  1. Reads the profile. Followers, total likes and number of posts, straight from the public account.
  2. Lists the last 60 posts. Every post with its views, likes, comments, shares, length and date.
  3. Works out the numbers. Average and median views, engagement rate, posts per week, best days, week by week.
  4. Sorts posts by format. Groups animations, collabs, brand deals and photo posts, and compares each to the account’s median.
  5. Writes you a plan. What to copy, what to skip, and the numbers to judge your own posts by.

A real run: @duolingo on TikTok · last 60 posts, 9 Sep – 13 Nov, November 18, 2026

The account at a glance

Last 60 posts, read on 18 Nov 2026.

Duolingo (@duolingo)

Views per post, week by week

Average vs median of each week’s posts.

100 = 3.1M views (week of 9 Nov average), September 7, 2026 – November 9, 2026.

Which formats beat its usual

The 60 posts, grouped by hand.

FormatPostsMedian viewsEngagement
Animations credited to an artist (🎨 @leah, @brerbo)102.25M21.9%
Other Duo skits and memes30953K17.1%
K-pop collabs (ILLIT, JISOO, LE SSERAFIM)7736K19.5%
Photo posts4584K17.2%
Brand tie-ins (Taco Bell, Brawl Stars, NYFW, Duo TV)9245K6.9%

Posting rhythm

Posts and median views by weekday.

DayPostsMedian views
Monday12604K
Tuesday11940K
Wednesday11507K
Thursday131.1M
Friday11969K
Saturday2536K
Sunday0–

Its best videos

Most viewed of the 60.

The takeaway: The typical post stayed flat; the hits got bigger. 6 of 60 posts passed 5M, and the artist animations are the format that keeps producing them.

The plan your AI writes

  1. Judge posts by the median, not the average. Duolingo’s average is 1.74M, but its typical post does 718K, and the top 5 posts bring 43% of all views. Use the median of your last 30 posts as your bar: anything 3× above it is a format to repeat.
  2. Find your “artist animation” and make more of it. The 10 posts credited to an animator (🎨 @leah, @brerbo) have a 2.25M median, 3× the account’s, and include 9.4M and 6.5M hits. Your own best format is in your numbers: group your posts and look for the one that keeps winning.
  3. Make brand deals look like the feed. The 9 Taco Bell, NYFW, Brawl Stars and Duo TV posts sit at a 245K median and 6.9% engagement, and get shared 5× less than the animations. The best of them, the drive-thru “Duo Habanero sauce” skit, did 638K because it looks like a normal Duo post.
  4. Post on weekdays, and ask for comments. Duolingo posts almost only Monday to Friday, with Thursday the best median (1.1M). Comments are rare, 0.3% of views, except when the caption asks: “translate this. wrong answers only” pulled 17,200 comments on 309K views, 18× the usual.

How this was made. Asked once in Claude with Whizbrew connected, on 18 November 2026. It read @duolingo’s public TikTok profile, its last 60 posts (9 September to 13 November 2026) with views, likes, comments, shares and length, and Whizbrew’s creator analytics on the last 20. Engagement rate here is likes + comments + shares divided by views, over the 60 posts; the follower-based rate (2.8%) is from the 20-post analytics. Formats were grouped by hand from the captions. Newer posts have had less time to collect views, so the last week’s median runs low. Watch time, profile visits and audience location are private: only the account owner sees them. Cost of the whole run: about 1 cent.

Without live data

I can’t open TikTok, so I can’t see @duolingo’s recent posts or their views. Duolingo is known for its unhinged owl mascot and strong engagement, and big brand accounts usually see an engagement rate of around…

Questions

Can you see TikTok analytics for other users?

You can see everything that’s public: followers, total likes, and every post’s views, likes, comments, shares, length and date. From those your AI works out average and median views, engagement rate, posting rhythm and the best formats. Watch time, profile visitors, traffic sources and audience location stay private, in the owner’s TikTok Studio.

How do you calculate TikTok engagement rate?

The usual formula is likes + comments + shares divided by views, per post or summed over recent posts. Some tools divide by followers instead, which gives a much smaller number: Duolingo is at 18.4% of views but 2.8% of followers. Always compare accounts with the same formula.

What’s a good engagement rate on TikTok?

It depends on the formula and the account’s size, so the honest benchmark is accounts like yours. Ask your AI to run the same numbers on 3 to 5 accounts in your niche and see where you sit. For scale: Duolingo, one of TikTok’s most loved brand accounts, gets 18.4% of views, and its brand tie-ins only 6.9%.

Can ChatGPT or Claude analyze a TikTok account?

Not on their own: they can’t open TikTok, so they guess from what they’ve read. Connected to Whizbrew, they read the live profile and posts, do the math and compare as many accounts as you name.

Are TikTok analytics accurate?

The public counts come straight from TikTok: views, likes, comments and shares as TikTok shows them, read the moment you ask. Big numbers are rounded by TikTok (14.6M), and newer posts are still collecting views, so compare posts of a similar age.

What does it cost?

You get $2 of free credit when you sign up, with no dashboard to learn. Each lookup costs a fraction of a cent, and lookups that find nothing are free. The run on this page cost about 1 cent.

Are you an AI agent? Start here.

You can open a Whizbrew account on your own: no email, no sign-up form, no key to paste. One request gives you a key that works at once, with free credit. Your human claims the account later.

# 1. Read what Whizbrew is, what a call costs and how to connect
curl -s https://whizbrew.com/llms.txt

# 2. Open your own account: one request, no email
curl -s -X POST https://whizbrew.com/v1/agent/start \
  -H 'content-type: application/json' \
  -d '{"agent":"<your name>"}'

# 3. Your human claims the account within 7 days. The whole flow:
curl -s https://whizbrew.com/agents.md

Not an agent? Paste this line into yours: Set up Whizbrew for me: read https://whizbrew.com/llms.txt and follow it.

More use cases

AI agents: Whizbrew is one MCP server and one API for 890 live marketing data tools in 25 groups, paid per call: a typical call costs $0.002 ($2 per 1,000 calls), prices run from $0.001 to $0.52 a call, only a call that returns data is charged (an empty or failed call is free), and there is no subscription. A new account starts with $2 of free credit, about 1,000 typical calls, with no card. Start with no account and no email: https://whizbrew.com/agents.md (a free quote for your task, then a key with the free credit). What Whizbrew is, what a call costs, how to connect: https://whizbrew.com/llms.txt. Prices: https://whizbrew.com/pricing, as data https://whizbrew.com/manifest.json. Every tool with its price: https://whizbrew.com/tools, as data https://whizbrew.com/v1/tools. Docs: https://whizbrew.com/docs.