Data to AI™ / Claude/TikTok
Ask Claude why a TikTok video held viewers, where its views came from and what commenters said, in one conversation instead of three exports.
Better answers, fewer tokens.
Claude
How did our TikTok followers change week by week in September, and when did we lose most?
The account gained 6,210 net followers over four weeks. Losses peaked in the week of 8 Sep at 1,150, and 22-28 Sep was the strongest week with 2,500 net.
| Week | Daily New Followers | Daily Lost Followers | Daily Total Followers |
|---|---|---|---|
| 1-7 Sep Profile Daily Insights | 1,840 | 420 | 1,420 |
| 8-14 Sep Profile Daily Insights | 2,310 | 1,150 | 1,160 |
| 15-21 Sep Profile Daily Insights | 1,520 | 390 | 1,130 |
| 22-28 Sep Profile Daily Insights | 2,960 | 460 | 2,500 |
Daily Total Followers is the daily net change in followers, not the follower count, so it is summed per week.
TikTok Organic extracts non-paid insights from a TikTok business account: daily profile activity, follower audience breakdowns, and per-video reach, watch time, retention, traffic sources and comments.
Using Video Lifetime View Retention, at which Second does Percentage fall below 50 for our last 20 videos, and which ones hold longest?
Claude reads retention next to Video Lifetime Engagement Distribution, explains where viewers leave and where likes cluster, and drafts notes on openings for the next shoot.
Group comment Text from Video Comments Lifetime Insights by topic for last month and show the Reach of the videos behind each topic.
Community managers learn which subjects start conversations on high-reach posts without reading every thread, because Claude ties each comment theme to its Video ID and Reach.
Query Video Lifetime Insights through the dataddo server and write this week's top videos by Full Video Watched Rate to reports/tiktok-weekly.md.
In Claude Code, a marketing analyst keeps the weekly TikTok summary as markdown next to the dashboard code, so notes stay in git history and reviewers see exactly what changed.
Data to AI™ is priced per seat, like the AI assistants your team already uses, with ~25% off on annual billing. Need tailored contracts or volume pricing? Talk to us about Enterprise.
Serve governed business data to Claude, ChatGPT and other AI tools over MCP.
per seat, billed monthly per seat, billed annually
Flexibly deploy Dataddo in any cloud or hybrid environment.
We have a payment model that works for you
| Without Dataddo |
With Dataddo
|
Outcome for you | |
|---|---|---|---|
| Lifetime numbers over time | Video metrics are lifetime totals, so seeing weekly change means keeping old exports and diffing them by hand before pasting anything into Claude. | Runs appended with dataddo_extraction_timestamp keep dated snapshots of Video Lifetime Insights, and Claude compares one snapshot with the next. | Weekly change per video |
| Retention and traffic tables | Columns like Second and Percentage arrive without context, so Claude has to guess whether a figure means retention, likes or traffic share. | Video Lifetime View Retention, Engagement Distribution and Traffic Sources reach Claude as separate entities with descriptions, so each Percentage is read correctly. | No mixed-up percentages |
| Team access in Claude | Every marketer uploads their own TikTok file into a personal chat, and the answers drift apart within a week. | On Team and Enterprise an Owner adds Dataddo Data Access once, and each member signs in with their own Dataddo account. | One setup, personal sign-in |
| Token consumption | Claude spends tokens exploring raw TikTok columns, sampling rows and retrying until it understands the data. | Field definitions and relations are supplied up front, so the model skips the exploration and goes straight to the answer. | Fewer tokens per answer |
| Answer quality | Prone to wrong joins, invented fields and numbers that are hard to check. | Answers grounded in defined fields. In the Dataddo benchmark, 78.5% of questions were answered correctly, against 65.5% with plain CSV files. | Better answers |
The TikTok datasets marketing teams use most, with their real field names. Claude queries them by name through the Dataddo semantic layer.
List of curated datasets
Need a dataset, metric, or attribute you don't see?
Tell us what's missing and we'll add it to the connector.
Runs on the schedule you set. Only Profile Daily Insights reads a relative window such as yesterday; the video and audience datasets are lifetime snapshots, so append them with dataddo_extraction_timestamp to track change.
TikTok connector →We asked 43 pre-registered questions of three real datasets - Google Search Console, HubSpot deals and Google Ads - and delivered the same rows to the same model in four ways. Only the data layer changed.
of questions answered correctly - the best of the four delivery methods tested
fewer confidently wrong answers - 14.0% of runs against 24.0% and 26.3%
more correct answers on messy CRM data - better on 8 questions, worse on none
Same model, prompts and rows in every condition; 759 graded runs, ground truth frozen before any run. On Google Search Console alone, documented CSV files did as well as Data to AI™ - the advantage comes from messier data such as HubSpot deals.
Read the benchmark →Set up a TikTok Organic source in Dataddo with Video Lifetime Insights and Video Lifetime View Retention, and attach it to a Claude destination or AI Model. Then add the custom connector https://headless.dataddo.com/mcp-data in Claude and sign in with OAuth, or run claude mcp add in Claude Code.
Yes, if your source includes Video Comments Lifetime Insights. It holds comment Text, Likes and Replies per Video ID, so Claude can group recurring themes and connect them to each video's performance.
Yes. Run claude mcp add with the Dataddo URL, sign in with /mcp or claude mcp login dataddo, and query TikTok entities from the terminal while you work in a repository.
Only Profile Daily Insights is read by date range. Video datasets are lifetime snapshots, so day-to-day comparisons work once you append snapshots with the extraction timestamp.
Yes, with Video Lifetime Audience by Type. It splits each video's viewers into types such as New viewers, Returning viewers, Followers and Non-followers, with a Percentage for each.
You decide. Claude shows the connector's tool permissions, and for each tool you choose whether Claude may use it freely or must ask you first, for example for refresh.
Any plan. Free allows one custom connector, Pro and Max users add it themselves, and on Team and Enterprise an Owner adds it once while members sign in with their own Dataddo account.