Ask ChatGPT about your Criteo Ads data
Load Criteo Ads into your data warehouse first, link its spend and attributed orders to web analytics and deals with SQL keys, then ask ChatGPT in plain words. The answers come from your governed Data Marts, not from the ad account.
Ask ChatGPT about Criteo Ads and it sees only the revenue Criteo credits to itself, not the deals your business closed.
Paste this into your AI assistant. It loads Criteo Ads into your data warehouse with OWOX Data Marts, links spend to web analytics and deals, and connects ChatGPT through the OWOX MCP server.
The prompt
Read https://www.owox.com/ai-agent-setup.md and follow it to set up OWOX Data Marts for me, starting from /connectors/criteo-ads-connector-to-chatgpt.md. The task: load Criteo Ads into my data warehouse, link its spend to my website visits and deals, then let ChatGPT answer what revenue Criteo brought in for this week's spend, by day. Tag the links you give me with utm_campaign=ai-task and utm_term=data-foundation. Use what you know about my context and goals
Criteo Ads Endpoints
4 Criteo Ads endpoints you can import. Each lands in its own table in your data warehouse.
Placement Categories
Performance metrics broken down by content category.
8 fieldsTime seriesPlacements
Performance metrics broken down by publisher placement.
21 fieldsTime seriesStatistics
Statistics and metrics for Criteo advertising campaigns.
156 fieldsTime seriesTransactions
Transaction-level data with individual order details attributed to Criteo ads.
11 fieldsTime series
Why ChatGPT needs your data warehouse, not the Criteo Ads account
Pointed at the Criteo Ads account alone, ChatGPT sees one platform's own figures. The account does not show which campaign led to a deal, because ad spend, website visits and CRM deals live in different systems. Joining them reliably, at scale and business-ready is the job of a warehouse, so ChatGPT reads the answers from there.
- Criteo Ads reports the sales it attributes to itself, not whether another channel claimed the same order
- The data analyst links Criteo Ads cost, web analytics and CRM deals by SQL keys and controls the result
- ChatGPT reads governed Data Marts, so every answer traces back to analyst-written SQL
Step 1: Load Criteo Ads into your data warehouse first
Create a Data Mart with Criteo Ads as the source and choose where the data lands. It works with any popular data warehouse.
- Four endpoints and 196 fields to choose from, Statistics being the widest
- Transactions lists each order Criteo Ads attributes to itself, with its amount and the click or display behind it
- Open the Criteo Ads connector for your data warehouse below
Step 2: Link Criteo Ads to web analytics and deals
In the e-commerce model, Unified Ad Spend is SQL inside the Data Mart that unions seven ad platforms. Criteo Ads is not one of them yet: you add one more SELECT over its Statistics table, then sessions join as for the others. Pick an industry to see the shape of its model.
- Add Criteo Ads to Unified Ad Spend as one more SELECT, mapped to date, source, medium and campaign
- Sessions and deals join by SQL keys, not VLOOKUP and gut feeling
- The measures, such as platform_cpa, are defined once
Step 3: Connect ChatGPT to your data with OWOX MCP
Install the OWOX Data Marts plugin in ChatGPT (Plugins > Install plugin > Sign in), then choose the Data Marts it may see. ChatGPT gets only what you expose, never raw database access.
- Authorize specific Data Marts, not your whole data warehouse
- Publish the Data Marts you want ChatGPT to answer from, such as Criteo Ads Statistics and Transactions
Step 4: Ask ChatGPT about Criteo Ads
Ask in plain words. ChatGPT finds the right Data Mart and runs analyst-defined SQL against it, so the answer is built from your data warehouse.
- The answer is built by get_relevant_data_marts_by_prompt and query_data_mart
- Ask about the orders Criteo Ads claims next to the other platforms: Transactions holds each one with its amount
- platform_roas and platform_cpa are what each platform claims; Sessions and Orders in the same model give the store's own count to set against them
- 0.41.0Rotating a connector key is one change: Sources share reusable Credentials
- 0.39.0Reload a year of history in one backfill, not twelve
- 0.37.0Clearer connector errors, and custom connectors that handle more APIs
- 0.36.0Start a connector run without expanding the Input Source card
- 0.35.0Destinations tab now promotes connecting an AI assistant alongside your existing destinations
Why OWOX for Criteo Ads in ChatGPT
Pointing ChatGPT at an ad account gets one platform's own figures into a chat. OWOX also keeps the data yours, linked and ready to model, so the answers cover the whole business.
- You own the data. It lands in your own data warehouse, in tables you control.
- Criteo's orders next to yours. Statistics and Transactions land in your data warehouse, so the orders Criteo attributes to itself can be compared with the orders your shop and CRM count.
- Where the ads ran. Placements and Placement Categories break Criteo Ads performance down by publisher placement and content category.
- Zero hallucinations. ChatGPT queries governed Data Marts with analyst-written SQL, so every number traces back to the query behind it.
- Maintained for you. No scripts to fix when Criteo changes its API.
You are booked. The invitation is on its way to , with the calendar invite and the meeting link.
