Data to AI™ / Claude/TikTok Ads
Ask Claude which TikTok ad campaigns, creatives and audiences earn their budget, using paid data that refreshes on schedule instead of a CSV from Ads Manager.
Better answers, fewer tokens.
Claude
Which TikTok campaigns converted cheapest last month, and where did the budget go?
Spring Retargeting converted cheapest at $11.40 per conversion on the smallest budget. Creator Launch took the most Spend at $14,200 but cost $19.70 per conversion.
| Campaign name | Spend | Conversion | Cost per conversion |
|---|---|---|---|
| Spring Retargeting TikTok Insights | $4,560 | 400 | $11.40 |
| Creator Launch TikTok Insights | $14,200 | 721 | $19.70 |
| Prospecting Broad TikTok Insights | $9,850 | 612 | $16.09 |
Spend and Conversion come from a Basic report at campaign level summed by Stat Time Day; Cost per conversion is the monthly Spend divided by Conversion, not an average of daily values.
TikTok Ads extracts paid advertising data from TikTok Ads Manager advertiser accounts: spend, impressions, clicks and conversions by campaign, ad group or ad, audience breakdowns by age, gender, country and placement, campaign and ad group settings, ad creatives, Smart+ creative materials and Instant Form leads.
In the Basic report by ad, rank ads by 6-Second Video Views divided by 2-Second Video Views and show Spend and CTR next to each Ad name.
Claude separates ads that stop the scroll from ads that only collect two-second glances, so the creative team briefs new edits around openings that actually held viewers on TikTok.
From the TikTok Audience report, which Age and Gender pairs took over 10% of Spend last month with a CPA above the account average?
The paid social lead gets a short list of segments to exclude or bid down, with the CPA gap for each, instead of scrolling through breakdown tabs in TikTok Ads Manager.
Join Ads with the Basic report by ad through the dataddo server and write the Ad Text of the five ads with the lowest cost per conversion to briefs/tiktok-copy.md.
In Claude Code, a growth marketer keeps creative briefs in the same repository as landing pages. The brief quotes real ad copy and the query that picked it, so the next round starts from evidence.
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.
$10.49/month
per seat
3 seats minimum
Flexibly deploy Dataddo in any cloud or hybrid environment.
Custom
We have a payment model that works for you
| Without Dataddo |
With Dataddo
|
Outcome for you | |
|---|---|---|---|
| Creative and copy in one place | Ad copy sits in one export and video metrics in another, so someone pastes both into the chat and hopes the Ad name values match. | Claude reads the Ads dataset with Ad Text and Landing Page URL next to ad-level TikTok Insights, joined by the semantic layer. | Copy reviewed against results |
| Paid versus organic | TikTok Ads Manager and TikTok Studio numbers end up in the same spreadsheet, and paid views get mixed with organic reach. | The TikTok Ads connector only holds advertiser account data, so Claude answers paid questions without organic posts in the way. | Clean paid-only answers |
| Reusable analysis in code | An analyst rebuilds cost per conversion formulas in a notebook every time the export columns are renamed. | Claude Code queries TikTok Ads through the dataddo server while you write scripts, so field names such as Spend and Conversion come from Dataddo. | Scripts that survive column changes |
| Token consumption | Claude spends tokens exploring raw TikTok Ads 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 Ads datasets marketing teams use most, with their real field names. Claude queries them by name through the Dataddo semantic layer.
| Dataset | Metrics and attributes |
Ask Claude
|
|---|---|---|
| TikTok Insights: Basic report by campaign |
|
Which TikTok campaigns had the lowest Cost per conversion last month, and how much Spend did each take? |
| TikTok Insights: Basic report by ad |
|
Which TikTok ads keep viewers to the end, comparing Video Views at 100% with Video Views? |
| TikTok Insights: Audience report |
|
Which Age and Gender groups took the most Spend on TikTok but returned the highest CPA? |
| Campaigns |
|
Which active TikTok campaigns have the largest Budget, and what Objective Type does each use? |
| Ad Groups |
|
Which ad groups have a Schedule End Time in the next seven days, and what Budget do they hold? |
| Ads |
|
Which Ad Text variations do we run in each campaign, by Campaign Name? |
| Smart+ Creatives Metrics by Campaign |
|
Which Smart+ creative materials took the most Spend in each campaign? |
| Lead Generation Leads |
|
How many Instant Form leads did each Campaign Name collect last week? |
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 →Create a TikTok Ads source in Dataddo, authorized with TikTok sign-in, using TikTok Insights reports such as a Basic report by campaign. Attach it to a Claude destination or AI Model. In Claude, connect Dataddo Data Access from the connectors directory and sign in; Claude Code then has it too.
No. Claude reads TikTok Ads data that Dataddo has already extracted, through the semantic layer. Dataddo never accepts SQL from the model, and nothing is written back to TikTok, so budgets and ads stay as they are.
No. TikTok Ads covers paid campaigns, ad groups, ads, spend and conversions from your advertiser accounts. Profile followers and organic video insights come from the separate TikTok Organic connector, which has its own Claude page.
TikTok Insights and Ads read a relative date range that moves forward on each run, and a new source starts from that window. Run a full data re-sync with a wider range to give Claude older months.
Yes, if you create a TikTok Insights source with the Audience report type and pick dimensions such as Age, Gender, Country Code or Placement Type. The Basic report type does not carry these breakdowns.
Yes. Signed in with your Claude account, Claude Code loads the same Dataddo connector, so you can query TikTok campaigns and ads from the terminal while you work in a repository.
Claude lists the connector's tool permissions, and you choose for each tool whether Claude may use it freely or must ask first. On Team and Enterprise, each member signs in with their own Dataddo account.
