Data to AI™ / Gemini/Marketo
Pull Marketo leads and activity logs into the terminal or VS Code, so marketing engineers build attribution inputs and data checks without a Marketo API client on their laptop.
Better answers, fewer tokens.
Gemini CLI
Which lead sources brought the most new leads in September, and how well are they scored?
Webinar brought the most new leads, 1,240, with an average Lead Score of 46. Paid Search added 980 leads but scored lower, at 21 on average.
| Lead Source | Leads | Lead Score |
|---|---|---|
| Webinar Leads | 1,240 | 46 |
| Paid Search Leads | 980 | 21 |
| Trade Show Leads | 410 | 38 |
Leads covers records whose Created At falls in the source's date window; Lead Score is averaged per source, not summed.
Adobe Marketo Engage is a marketing automation platform for email, lead management and scoring. Dataddo extracts one flexible Marketo dataset: pick the Leads or Activities object and the fields you need, including custom lead fields from your instance, so marketing ops can ask about lead flow and engagement in plain language.
Join Fill Out Form and Click Email activities to Leads by Lead Id for the last 30 days and write attribution/touchpoints.csv with Activity Date, Activity Type Name and Lead Source.
A marketing analyst feeds the attribution notebook from Gemini CLI, so the multi-touch model runs on fresh touchpoints without a manual export each month.
Count Marketo leads by Lead Status with Created At in the last 7 days, compare with tests/fixtures/lead-status.json and list the rows that differ.
Before a funnel dashboard ships, a data engineer runs the check in the terminal against the latest Marketo extraction and stops the release when counts drift.
Sample Change Data Value activities and write src/marketo/parse-attributes.ts that turns the Attributes column into typed old and new values.
A developer in VS Code asks Gemini Code Assist in agent mode for the parser, built from real activity rows instead of guesses about the payload.
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 | |
|---|---|---|---|
| Marketo access from scripts | An engineer registers a LaunchPoint service, writes bulk export polling code and handles the 31-day limit before getting a single row. | Dataddo runs the bulk exports on schedule, and Gemini CLI queries the extracted Leads and Activities by entity and field name. | No export code to maintain |
| Activity type IDs | Scripts hardcode activity type numbers, which can differ between Marketo instances, and break on the next subscription. | Activity Type Name is filled from your own instance's activity types, so Gemini filters on names such as Fill Out Form. | Readable activity filters |
| Credentials on the laptop | A Marketo Client Secret sits in a .env file on every machine that runs the attribution scripts. | Marketo is authorized once in Dataddo; Gemini CLI keeps only Dataddo sign-in tokens in ~/.gemini/mcp-oauth-tokens.json and renews them. | No Marketo secret in the repo |
| Control in the terminal | A script with API access runs every request it was written for, without a prompt before each one. | Gemini CLI asks you to confirm each Dataddo tool call, and you choose Always allow only for the tools you trust. | Each lookup approved |
| Token consumption | Gemini spends tokens exploring raw Marketo 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 Marketo datasets marketing teams use most, with their real field names. Gemini queries them by name through the Dataddo semantic layer.
| Dataset | Metrics and attributes |
Ask Gemini
|
|---|---|---|
| Leads: source and status |
|
Write leads created last week with Lead Source, Lead Status and Lead Score to a CSV for the funnel notebook. |
| Leads: company and contactability |
|
Count new leads with an empty Industry or Annual Revenue so the enrichment job can be checked before release. |
| Activities: email engagement |
|
Export Email Bounced and Unsubscribe Email activities with Lead Id and Activity Date to a CSV for the list hygiene script. |
| Activities: forms and web visits |
|
Return daily Fill Out Form counts by Activity Date for the last 30 days as JSON for the landing page test. |
| Activities: scoring and data changes |
|
Write Change Score activities with Lead Id, Campaign Id and Attributes to a file the scoring model review can load. |
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 a Marketo source in Dataddo with the Leads or Activities object and attach it to a Google Gemini destination or AI Model. In ~/.gemini/settings.json, add a dataddo server under mcpServers with httpUrl https://headless.dataddo.com/mcp-data, restart Gemini CLI, run /mcp auth dataddo and sign in.
Attach the Marketo flow to a Google Gemini destination or AI Model in Dataddo. Add the dataddo server with httpUrl to settings.json, restart Gemini CLI, run /mcp auth dataddo and check /mcp.
In Gemini CLI, url falls back to SSE, which Dataddo does not support. Use httpUrl and leave out headers and any oauth block; sign-in runs through /mcp auth dataddo.
Yes. When you pick the Activities object, the optional Activity Type filter keeps only the types you select, such as Click Email or Change Score, which keeps the data Gemini reads small.
Yes. Once signed in, Gemini reaches every flow or Context attached to an AI destination or AI Model in that Dataddo account, not only the Google Gemini ones.
No. Gemini queries extracted Marketo data through the semantic layer by entity and field name. Dataddo never accepts SQL from the model, and nothing is written back to Marketo.
Your Dataddo email and password, with MFA if prompted; Google and Microsoft SSO are not offered here. Gemini CLI opens the sign-in page in a browser on the same machine.
