Data to AI™ / Claude/Amazon Ads
Ask Claude which campaigns, search terms and ASINs earn their spend across Sponsored Products, Sponsored Brands and DSP, without downloading a single report.
Less tokens, better answers.
Claude
Which Sponsored Products campaigns had the highest ACOS on 14-day sales last month?
Generic - Kitchen ran the highest ACOS at 42.0%, more than four times Brand - Exact at 10.0%. Competitor ASINs came second at 33.0%.
| Campaign Name | Spend | Sales 14d | Acos Clicks 14d |
|---|---|---|---|
| Generic - Kitchen Sponsored Products: Campaign | 4,120 | 9,810 | 42.0% |
| Competitor ASINs Sponsored Products: Campaign | 2,460 | 7,450 | 33.0% |
| Brand - Exact Sponsored Products: Campaign | 1,350 | 13,500 | 10.0% |
Spend and Sales 14d use the same 14-day attribution window; Sales 7d is never mixed in.
Amazon Ads reports cover Sponsored Products, Sponsored Brands, Sponsored Display and Amazon DSP. Each source reads one report type for the profile you pick, daily or as a summary for the date range.
Which Search Term values had Cost above 50 in the last 30 days but zero Purchases 7d? Show the Keyword and Match Type behind each.
Every Monday a PPC manager asks Claude for search terms that spend without converting. Claude groups them by Keyword and Match Type and drafts a negative list you review before editing campaigns.
Query the Sponsored Products Campaign entity through the dataddo server, sort by Acos Clicks 14d and refresh reports/amazon-acos.md with Spend and Sales 14d.
The retail media summary lives next to the reporting code. Claude Code pulls Acos Clicks 14d and Roas Clicks 14d per campaign and updates the markdown file the team reviews in a pull request.
What share of Sponsored Brands Sales came from New To Brand Sales in each of the last six weeks, split by Campaign Name?
Brand managers want to know whether Sponsored Brands wins new customers or mostly recaptures existing ones. Claude returns the weekly ratio as a table for the quarterly brand review.
Data to AI™ is free while in private pre-release. We onboard teams in waves and shape the product with their feedback. At launch, it will be priced like the AI assistants your team already uses. Need tailored contracts or volume pricing? Talk to us about Enterprise.
Serve governed business data to Claude, ChatGPT and other AI tools over MCP.
Free during pre-release
Flexibly deploy Dataddo in any cloud or hybrid environment.
We have a payment model that works for you
| Without Dataddo |
With Dataddo
|
Outcome for you | |
|---|---|---|---|
| Getting reports into Claude | Someone downloads a CSV per Amazon report type, cleans the headers and uploads the files to a Claude chat before every review. | Claude queries the attached Amazon Ads report sources through the Dataddo Data Access connector whenever a question needs them. | No more report downloads |
| Attribution windows | Uploaded files show Sales 7d and Sales 14d side by side with no explanation, so Claude can mix windows inside one ACOS figure. | The semantic layer describes each field, so Claude knows that Sales 14d and Purchases 7d belong to different attribution windows. | ACOS on one window |
| Working from a repository | A script requests Amazon reports, polls until each one is ready and maps columns before anyone can analyze the output in code. | Claude Code connects with claude mcp add, signs in with /mcp and reads the same report entities as Claude in the browser. | Same data in chat and code |
| Access for the team | Each analyst keeps a private export folder, and the files in shared Claude projects drift apart as they age. | On Team and Enterprise an Owner adds the connector once, and every member signs in with their own Dataddo account. | One setup for everyone |
| Token consumption | Claude spends tokens exploring raw Amazon 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. | Less 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 Amazon Ads datasets marketing teams use most, with their real field names. Claude queries them by name through the Dataddo semantic layer.
Runs on the schedule you set over a relative date range, for example yesterday, that moves forward on every run. Older periods are loaded with a full data re-sync, and new data can lag while Amazon generates the report.
Amazon Ads connector →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 Amazon Ads sources in Dataddo, one per report type such as Sponsored Products Campaign or Search Term, and attach them to a Claude destination or AI Model. In Claude, add a custom connector with the URL https://headless.dataddo.com/mcp-data and sign in. In Claude Code, run claude mcp add and authenticate with /mcp.
Yes, with a source for each. Every report type has its own API endpoint, so each is extracted separately, and Claude queries all of them through one connector.
Amazon report generation depends on its API traffic, so new rows can arrive late. Ask Claude to run data_status to see when the flow last updated.
The one you name. Fields carry their window, such as Sales 7d or Acos Clicks 14d, so state it in your prompt.
Yes. Run claude mcp add with the Dataddo URL and sign in with /mcp. Claude Code then reads the same report entities inside your repository.
No. Claude only reads extracted data by entity and field name. You still change bids, budgets and negatives in Amazon Ads.
What the attached flow holds. A new source starts from its relative date range, so load earlier periods with a full data re-sync.