Agent context
Tiktok Ads models
3 SQL models that turn the raw Tiktok Ads tables into the reports people ask about. Deploy them in Weld and your agent queries the definitions behind every number.
How the set is built
- 5Raw tables
- 5Staging
- 4Core
- 3Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Ad group performance dailyDaily performance per ad group, labelled with the optimisation goal and event that define what "conversions" means for it. This is the level to read cost per conversion at: within one ad group the conversions are a single event type.grain: date_day x account_id x ad_group_id · 5 raw tables
- Ad performance dailyDaily delivery and conversion results per ad, the Ads Manager "Ads" tab by day.grain: date_day x account_id x ad_id · 5 raw tables
- Campaign performance dailyDaily campaign performance with the rates Ads Manager shows: CTR, CPC, CPM, cost per conversion and Complete payment ROAS.grain: date_day x account_id x campaign_id · 5 raw tables
- Weld or dbt
- The same SQL in both dialects. Sync the folder with GitHub Sync, or copy the dbt models into your project.
- Check before you rely on it
- Reconcile a month against Tiktok Ads's own reports first. Each model's notes say what the synced data can and can't support.
Connect Tiktok Ads.
Your agents start with context.
Sync Tiktok Ads to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.