Data to AI™ / Copilot/HubSpot
Give RevOps and finance a Teams agent that answers pipeline, stage and closed won questions from HubSpot, without anyone exporting the deals board.
Less tokens, better answers.
Microsoft 365 Copilot
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.
@Deal desk Which Deals reached a closed won Stage Label this week, and which owner holds each one?
On Friday afternoon finance mentions the agent in the RevOps channel instead of asking a rep to export the board, with owner names blended in from Owners.
@Deal desk List the Line Items on deals won last month so I can compare them with the invoices we raised.
A billing specialist asks the agent before month-end close to catch deals that were signed in HubSpot but never invoiced to the customer.
Describe Properties History through the dataddo tools and write a function that returns days between dealstage changes using Timestamp.
A dashboard developer in VS Code implements the metric against the real Property Name, Value and Timestamp fields rather than a hand-made sample file.
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 | |
|---|---|---|---|
| Where answers happen | RevOps fields the same deal questions in Teams chats every week and answers each one by exporting the board. | A Copilot Studio agent published to Teams answers from Deals, Deal Pipelines and Owners whenever someone mentions it. | Self-serve in Teams |
| Owner names | Deals carry hubspot_owner_id, so an answer in a Teams thread lists numbers instead of the people responsible. | Blend the Owners dataset on Owner ID, so the agent replies with the First Name and Last Name of each owner. | People, not IDs |
| Routing deal questions | Microsoft 365 Copilot has no way to know that deal questions belong to HubSpot rather than files in SharePoint. | Describe the Dataddo tool as the source for HubSpot deals, pipeline stages and owners; Copilot Studio uses that text to decide when to call it. | Deal questions hit CRM data |
| Reps who left | When a rep leaves, their deals point to an owner nobody can find in the current user list. | The Owners Archived dataset keeps deactivated owners, so the agent can still name who held each deal. | No orphaned deals |
| Token consumption | Copilot 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. Copilot 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 →Sync HubSpot Deals, Deal Pipelines and Owners in Dataddo and attach the flow to a Copilot destination or AI Model. In Copilot Studio, add a Model Context Protocol tool pointing to https://headless.dataddo.com/mcp-data with OAuth 2.0 dynamic discovery, then publish the agent to Teams. For GitHub Copilot, add the URL to .vscode/mcp.json.
Through Copilot Studio. Add Dataddo Data Access to an agent as a Model Context Protocol tool, sign in with OAuth and publish under Channels > Teams and Microsoft Copilot.
Name what it covers, such as HubSpot deals, pipeline stages and owners. The description tells the agent when to call Dataddo.
Yes. Add the Dataddo server to .vscode/mcp.json, start it, sign in and open Copilot Chat in Agent mode. On Copilot Business and Enterprise, an org admin has to enable the MCP servers in Copilot policy.
Each run pulls the current list of deals and HubSpot cannot load past states. To compare weeks, add the extraction timestamp and append runs, so the agent can read earlier snapshots.
No. The agent reads HubSpot data that Dataddo has already extracted and cannot write to HubSpot. Stage changes are made in HubSpot and arrive with the next run.
No. The HubSpot account that authorizes Dataddo needs at least admin-level permissions. People using the agent never sign in to HubSpot; the agent reaches the data through Dataddo.