Data to AI™ / Copilot/TikTok Ads
Give the paid social team an agent in Teams that answers TikTok Ads spend, country and ad group questions, so nobody waits for the weekly media report.
Better answers, fewer tokens.
Microsoft 365 Copilot
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.
@Paid Social What did each TikTok campaign spend yesterday by Stat Time Day, and which Campaign name had the highest Cost per conversion?
Account managers ask the agent in the Teams channel each morning instead of logging in to every advertiser account, and talk through the outliers right in the thread.
@Paid Social Split last month's TikTok Spend and Conversion by Country Code from the Audience report, as a table I can paste into PowerPoint.
In Microsoft 365 Copilot, the agent returns the country table while you write the monthly client deck, so the slide matches the numbers the team saw in Teams.
Use the dataddo tools to list Ad Groups with a Schedule End Time in the next 14 days and add them to our flight calendar config.
In VS Code, GitHub Copilot in Agent mode reads real ad group names, budgets and end dates, so a marketing engineer keeps the internal flight calendar in sync without asking for exports.
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 | |
|---|---|---|---|
| Answers where the team talks | The media buyer exports TikTok Ads Manager reports, shares them in Teams, and every follow-up waits for the next export. | The Copilot Studio agent sits in the channel and answers spend and conversion questions from the scheduled TikTok Ads flow. | No waiting for the media report |
| Many advertiser accounts | Agencies repeat the same TikTok export for each client advertiser account, then merge the files by hand. | Multi-account extraction, enabled by the Dataddo Solutions team, pulls the same data from every TikTok Ads account. | One agent across accounts |
| When the agent calls Dataddo | A general assistant cannot tell which questions need TikTok ad data, so people paste numbers into prompts. | The server description in Copilot Studio tells the agent to call Dataddo for TikTok spend, conversion and audience questions. | Ad questions routed to ad data |
| Flight dates | Ad group end dates live in TikTok Ads Manager only, so campaigns run out before anyone plans the next flight. | The Ad Groups dataset holds Schedule End Time, Budget and Optimization Goal, which the agent reads on request. | Fewer surprise end dates |
| Token consumption | Copilot 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. Copilot queries them by name through the Dataddo semantic layer.
| Dataset | Metrics and attributes |
Ask Copilot
|
|---|---|---|
| TikTok Insights: Basic report by campaign |
|
Which campaigns earned the highest Complete Payment ROAS on TikTok last quarter? |
| TikTok Insights: Basic report by ad |
|
Which ad groups spend the most per Video Views, grouped by Ad group name? |
| TikTok Insights: Audience report |
|
Which Placement Type brings the most Conversion for the same budget? |
| Campaigns |
|
Which campaigns have an Operation Status of enabled but a Secondary Status that blocks delivery? |
| Ad Groups |
|
Which ad groups use a different Bid Type than the rest of their Campaign Name? |
| Ads |
|
How many ads of each Ad Format are live, based on Operation Status? |
| Smart+ Creatives Metrics by Campaign |
|
Which Main Material Name has high Impressions but almost no Clicks? |
| Lead Generation Leads |
|
Which Ad ID produced the most leads in the last 30 days? |
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 Ads source in Dataddo with TikTok Insights reports and the Ad Groups dataset, and attach it to a Copilot destination or AI Model. In Copilot Studio, add https://headless.dataddo.com/mcp-data as a Model Context Protocol tool with OAuth 2.0, then publish the agent to Teams and Microsoft 365 Copilot.
Yes. Dataddo connects as an MCP tool on a Copilot Studio agent. After you publish it to Microsoft 365 Copilot and Teams, people reach the TikTok Ads data by typing @ and selecting the agent.
Write a clear server description in Copilot Studio. It tells the agent when to call Dataddo, for example only for TikTok spend, conversion and audience questions.
Yes. Add the Dataddo server to .vscode/mcp.json, start it, sign in and use Copilot Chat in Agent mode. On Business and Enterprise an organization admin first enables MCP servers in Copilot policy.
When you create the authorizer in Dataddo, choose TikTok to sign in and approve access, which is recommended, or TikTok Custom to use your own app credentials. The agent never sees these credentials.
No. The agent reads TikTok Ads data that Dataddo extracted, through the semantic layer, and Dataddo never accepts SQL from the model. Budget and status changes still happen in TikTok Ads Manager.
Not through this source. TikTok Ads holds paid advertiser data only. Organic profile and video insights come from the TikTok Organic connector, which you can attach to the same agent as a separate flow.
