Data to AI™ / Gemini/Pipedrive
Pull Pipedrive deals, stage settings and custom field keys into the terminal or VS Code, so RevOps engineers build forecast inputs and checks without a Pipedrive API token on their laptop.
Better answers, fewer tokens.
Gemini CLI
Which reps carry the most weighted pipeline expected to close in September?
Open deals expected to close in September add up to €412,000, or €171,500 weighted. Marta Novak holds €82,000 of the weighted value, almost half.
| Owner Name | Value | Weighted Value |
|---|---|---|
| Marta Novak Deals | €168,000 | €82,000 |
| Tom Reyes Deals | €141,000 | €54,500 |
| Lena Brandt Deals | €103,000 | €35,000 |
Deals pulls all current records on every run, so open deals reflect the last extraction rather than a date window.
Pipedrive is a CRM for sales teams that manages leads, deals and the sales pipeline. Dataddo extracts deals, stages, pipelines, activities, leads and deal subscriptions, so RevOps can ask about pipeline and forecast in plain language.
Count Deals by Status and sum Value per Owner Name, then compare the totals with fixtures/pipeline-expected.json and tell me which rows differ.
Before a new revenue dashboard ships, a data engineer runs the check in Gemini CLI against the latest Pipedrive extraction and blocks the release when totals drift.
Read Deals Timeline for the last two quarters, group the free-text Lost Reason values into at most eight categories and save the mapping to analysis/lost-reasons.csv.
An analyst turns years of inconsistent loss notes into a clean category file in the repo, so the win-loss notebook stops splitting the same reason across five spellings.
Use the dataddo tools to list Fields on the deals Endpoint and generate src/pipedrive/fields.ts mapping each hashed Key to its Field Name and Field Type.
A developer in VS Code asks Gemini Code Assist in agent mode for the mapping, so the internal sync service reads custom deal fields by name instead of opaque keys.
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 | |
|---|---|---|---|
| Custom field keys in code | Developers copy hashed custom field keys out of Pipedrive settings by hand and hardcode them, and nobody notices when a field is renamed. | The Fields dataset returns Key, Field Name and Field Type per Endpoint, so Gemini regenerates the mapping file whenever the schema changes. | Field mapping stays current |
| Pre-release data checks | An engineer writes a one-off script against the Pipedrive API, handles pagination and rate limits, and deletes it after the release. | Gemini CLI queries extracted Deals and Stage through the semantic layer by entity and field name, and the check lives in the repo next to the dashboard. | Repeatable checks before deploy |
| Credentials on the laptop | A personal Pipedrive API token sits in a .env file on every machine that runs the scripts. | Pipedrive is authorized once in Dataddo; Gemini CLI keeps only Dataddo sign-in tokens in ~/.gemini/mcp-oauth-tokens.json and renews them automatically. | No CRM token in the repo |
| Control in the terminal | A script with full API access runs whatever it was written to do, with no prompt before each request. | Gemini CLI asks you to confirm each Dataddo tool call, and you can choose Always allow only for the tools you trust. | Each lookup approved |
| Token consumption | Gemini spends tokens exploring raw Pipedrive 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 Pipedrive datasets finance and RevOps teams use most, with their real field names. Gemini queries them by name through the Dataddo semantic layer.
| Dataset | Metrics and attributes |
Ask Gemini
|
|---|---|---|
| Deals |
|
Write open deals with Title, Value, Weighted Value and Expected Close Date to a CSV the forecast notebook can load. |
| Deals Timeline |
|
Return won Value per Period Start for the last 12 months as a table I can diff against our revenue model. |
| Stage |
|
Generate a JSON map from each stage Name to its Deal Probability, grouped by Pipeline Name, for the forecast script. |
| Activities |
|
Count activities per Type Name split by Done, so I can check the numbers before deploying the sales dashboard. |
| Leads |
|
List leads with Title, Source Name and UTM Campaign where UTM Campaign is empty, so the tracking setup can be fixed. |
| Deal Subscriptions |
|
Sum Cycle Amount by Cadence Type and write it to the revenue model's input file, with End Date for each subscription. |
| Fields |
|
Generate a TypeScript type from each Field Name, Key and Field Type on the deals Endpoint. |
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 Pipedrive source in Dataddo with Deals, Stage and Fields, 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 with your Dataddo account.
Attach the Pipedrive flow to a Google Gemini destination or AI Model in Dataddo. Then 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. Agent mode in VS Code reads the same settings.json as Gemini CLI. In IntelliJ, Gemini Code Assist uses its own mcp.json, so add the Dataddo server there.
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. Use a separate account to keep them apart.
No. Gemini queries extracted Pipedrive data through the semantic layer by entity and field name. Dataddo never accepts SQL from the model, and nothing is written back to Pipedrive.
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 web browser, so it needs a browser on the same machine.
