Ask ChatGPT about your LinkedIn Ads data
A LinkedIn Ads click can close a deal a year later. Load the campaigns into your data warehouse, link leads and deals by SQL keys, then ask ChatGPT which ones earned pipeline.
LinkedIn AdsConnectedAd AccountsAd AnalyticsAd Analytics by…Ad Analytics by…
ChatGPTDateCostClicksDaily 09:00ChatGPT can read what LinkedIn Ads cost, but not which campaigns led to deals that closed months later.
Paste this into your AI assistant. It loads LinkedIn Ads into your data warehouse, links campaigns to leads and deals, and connects ChatGPT to that Data Mart 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/linkedin-ads-connector-to-chatgpt.md. The task: connect ChatGPT to my LinkedIn Ads data and tell me our cost per qualified lead by campaign this quarter, with how many people each campaign reached. 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
LinkedIn Ads Endpoints
8 LinkedIn Ads endpoints you can import. Each lands in its own table in your data warehouse.
Ad Accounts
Your ad account settings, billing details, currency, and account status.
14 fieldsAd Analytics
Daily performance metrics for your campaigns — impressions, clicks, spend, and conversions.
104 fieldsTime seriesAd Analytics by Country
Daily campaign performance by the country of the members who saw your ads — impressions, clicks, spend, and conversions per country.
100 fieldsTime seriesAd Analytics by County
Daily campaign performance by the county of the members who saw your ads — impressions, clicks, spend, and conversions per county.
100 fieldsTime seriesAd Analytics by Region
Daily campaign performance by the region of the members who saw your ads — impressions, clicks, spend, and conversions per region.
100 fieldsTime seriesCampaign Groups
Top-level containers that group campaigns with shared objectives, budgets, and scheduling.
14 fieldsCampaigns
Individual campaigns defining your targeting, ad format, bid strategy, and budget.
29 fieldsCreatives
The visual and copy elements of your ads shown to members across LinkedIn.
14 fields
Why LinkedIn Ads does not go straight to ChatGPT
ChatGPT can read an ad account, but that shows what LinkedIn Ads cost, not which ad led to a deal that closed months later. Spend, website touch points and CRM deals sit apart, and the join, reliable and business-ready, belongs in a warehouse first.
- LinkedIn Ads shows what an ad cost; the deal it led to lives in your CRM
- In B2B an ad today can close a deal a year later, so the join belongs in your data warehouse
- ChatGPT answers from that linked data, controlled by the data analyst
LinkedIn AdsAd spendChatGPT
Data warehouseJoined by idStep 1: Load LinkedIn Ads into your data warehouse first
Create a Data Mart with LinkedIn Ads as the source and choose where the data lands. It works with any popular data warehouse.
- Five endpoints and 175 fields to choose from, each endpoint in its own table
- Ad Analytics by campaign, with creatives, campaign groups and account details around it
- Open the LinkedIn Ads connector for your data warehouse below
LinkedIn AdsData MartGoogle BigQuery
AWS Athena
Snowflake
AWS Redshift
Databrickslinkedin_ads.ad_analyticsStep 2: Link LinkedIn Ads to leads and deals
In your data warehouse the model merges LinkedIn Ads with your other ad platforms, then joins leads and campaign results by a key. Pick an industry to see the shape of its model.
- LinkedIn Ads spend lines up with Facebook Ads and Google Ads by date
- Lead-form leads and CRM deals meet by SQL keys, not VLOOKUP
- Measures such as cost_per_lead are defined once
LinkedIn AdsAd Analytics
Facebook AdsAd spend
Google AdsAd spendStep 3: Connect ChatGPT to your LinkedIn Ads data with OWOX MCP
Install the "OWOX Data Marts" plugin in ChatGPT (Plugins > Install plugin) and sign in. ChatGPT then sees the Data Marts you publish and queries them through MCP.
- Plugins > Install plugin, find "OWOX Data Marts" and sign in
- ChatGPT sees only the Data Marts you publish
ChatGPTConnectorsOWOX MCPAddConnectedStep 4: Ask ChatGPT which LinkedIn Ads campaigns lead to deals
Ask in plain words. ChatGPT finds the right Data Mart and queries it, so the numbers come from your data warehouse and not from a guess.
- Ask about a campaign, a campaign group or a creative in plain words
- The answer ties LinkedIn Ads spend and lead-form leads to pipeline, with measure names shown
ChatGPTWhich channel has the lowest cost_per_lead?get_relevant_data_marts_by_promptquery_data_martcost_per_leadpipeline_per_dollarStep 5: Export the answer to Google Sheets, CSV or XLS
Optional: in one click send ChatGPT's answer, or the data behind it, to Google Sheets, CSV or XLS to check it or share it.
- Verify the answer in a sheet before it goes to stakeholders
- One Data Mart feeds the chat, the sheet and the file
Google SheetsCSVXLSOne click
- 0.43.0Compare LinkedIn Ads results across markets: spend by country, region, and county
- 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
Why OWOX for LinkedIn Ads in ChatGPT
LinkedIn Ads in a chat shows what an ad cost. OWOX adds the deals it led to months later, from data you own.
- You own the data. It lands in your own data warehouse, in tables you control.
- Answers about the whole business. Ads, web analytics, CRM, deals and calls are linked, not copied from an ad account.
- Zero hallucinations on your data. ChatGPT answers from governed Data Marts and shows the measure names it used.
- Long B2B cycles covered. An ad today can close a deal a year later; the join lives in your data warehouse, not in a chat.
- Maintained for you. No scripts to fix when LinkedIn changes its API.
You are booked. The invitation is on its way to , with the calendar invite and the meeting link.