Data to AI™ / Claude/HubSpot
Get weighted pipeline, stage velocity and forecast-versus-actual answers from HubSpot deals in Claude, with stage IDs already turned into readable labels.
Less tokens, better answers.
Claude
How long did the deals we won in September spend in each stage?
The 23 deals won in September took 31 days on average from qualification to contract. Decision maker bought-in was the slowest stage, at 12 days or 39% of the cycle.
| Stage Label | Deals | Avg days in stage | Share of cycle |
|---|---|---|---|
| Qualified to buy Properties History | 23 | 6 | 19% |
| Presentation scheduled Properties History | 23 | 9 | 29% |
| Decision maker bought-in Properties History | 23 | 12 | 39% |
| Contract sent Properties History | 23 | 4 | 13% |
Days are measured between dealstage change Timestamps in Properties History, with Stage IDs mapped to Stage Label through Deal Pipelines.
HubSpot is a marketing, sales and service platform. Dataddo extracts its CRM records, such as deals, line items, quotes and owners, with custom fields on every object, plus pipeline stages and property change history.
Apply Stage Probability from Deal Pipelines to open Deals and show the weighted pipeline by Stage Label for this quarter.
Before the monthly finance review, the controller asks which stages carry most of the weighted pipeline and gets an explanation ready to paste into the review notes.
Use the dataddo server to read dealstage changes from Properties History and write median days per stage to analysis/deal-velocity.md.
A RevOps analyst keeps cycle-length assumptions in a repository. Claude Code computes them from Timestamp values, so the forecast inputs come from recorded stage changes, not memory.
Which open Deals have an hs_lastmodifieddate older than 21 days? Group them by owner, with First Name and Last Name from Owners.
Two weeks before quarter end, sales management checks who is sitting on untouched late-stage deals and rebalances them between reps before they slip.
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 | |
|---|---|---|---|
| Readable stages | A deals export shows dealstage as an internal ID, so someone maps IDs to stage names by hand before Claude can explain anything. | Blend Deal Pipelines on Stage ID, and Claude answers with Stage Label and can apply Stage Probability for weighted figures. | Stage names, not IDs |
| Time spent in each stage | An export shows only where each deal is today, so questions about how long deals wait in a stage have no data behind them. | Properties History records every dealstage change with its Value and Timestamp, so Claude can measure the days between changes. | Velocity from real changes |
| Rollout across RevOps | Every analyst uploads a different deals file, so the same question gets a different answer in each person's chat. | An Owner on a Team or Enterprise plan adds Dataddo Data Access for the organization, and people then log in with their personal Dataddo credentials. | Shared source of answers |
| Token consumption | Claude spends tokens exploring raw HubSpot 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 HubSpot datasets finance and RevOps teams use most, with their real field names. Claude queries them by name through the Dataddo semantic layer.
List of curated datasets
Need a dataset, metric, or attribute you don't see?
Tell us what's missing and we'll add it to the connector.
Runs on your schedule. Deals and Line Items pull all current records each run; Date Range variants and Properties History read a relative window. History cannot be backfilled, so keep snapshots with the extraction timestamp.
HubSpot 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 a HubSpot source in Dataddo with datasets such as Deals, Deal Pipelines and Properties History, and attach it to a Claude destination or AI Model. In Claude, add the custom connector https://headless.dataddo.com/mcp-data and sign in to Dataddo. For Claude Code, run claude mcp add --transport http dataddo with that URL.
Deals store dealstage as an ID. Add the Deal Pipelines dataset and blend it on Stage ID, so Claude can answer with Stage Label and use Stage Probability for weighted figures.
Only from the day you start keeping snapshots. HubSpot cannot load historical deal data, so add the Dataddo extraction timestamp and append each run. Properties History also covers past property changes.
Yes. Properties History returns who changed which property, the old and new value and when, for a chosen CRM object. Query it from your repository after claude mcp add.
Custom fields are supported for all HubSpot objects, so select them in the source. For custom objects, use the Custom Objects dataset with the object's ID from your HubSpot settings, or ask the Dataddo Solutions team.
The HubSpot account that authorizes Dataddo needs at least admin-level permissions. Claude users only sign in to Dataddo, and on Team and Enterprise each member uses their own Dataddo account.
Every plan supports custom connectors, with one allowed on Free. Pro and Max users add it on their own; on Team and Enterprise an Owner adds it for the whole organization.