Data to AI™ / Copilot/QuickBooks
Finance managers and budget holders read the balance sheet, deposits and department results from QuickBooks through a Copilot agent in Teams, without waiting for a report pack.
Less tokens, better answers.
Microsoft 365 Copilot
Which customers owe us the most, and how old is their oldest unpaid invoice?
Northwind Supply has the largest open balance, $19,400, almost as much as the next two customers combined ($22,460). Its oldest open invoice was due on 14 Jul.
| Customer name | Open balance | Oldest Due date |
|---|---|---|
| Northwind Supply AR Aging Detail Report | $19,400 | 14 Jul 2026 |
| Bluebird Studio AR Aging Detail Report | $12,180 | 3 Aug 2026 |
| Harbor Dental AR Aging Detail Report | $10,280 | 21 Aug 2026 |
Open balance comes from the AR Aging Detail Report, which pulls all current data on each run, not from summing invoice history.
QuickBooks is accounting software for small and medium businesses. Dataddo extracts its transactions and standard reports, from invoices and bills to AR and AP aging, cash flow and profit and loss.
@Books Assistant Sum Deposits Total Amount by Deposit To Account Name for last week, and show Balance Sheets V2 Total per Section.
The CFO asks the agent in Microsoft 365 Copilot for last week's deposits and balance sheet totals, then pastes the answer into the leadership update.
@Books Assistant For Dept Name Marketing, list Profit and Loss Detail rows this quarter by Category with Amount, largest first.
Budget holders mention the agent in their Teams channel to see what their department spent, so spending questions are settled in the thread rather than by an analyst.
Use the dataddo tools to describe Transaction Lines Report V2 and map Account name, Amount and Transaction date into our forecast actuals table.
A finance analyst who keeps the forecast model in a repository asks GitHub Copilot in Agent mode to write the mapping, so forecast and books use the same accounts.
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 | |
|---|---|---|---|
| Department figures for budget holders | Budget holders wait for finance to cut a Profit and Loss Detail export per department and send it round each month. | The agent in Teams answers per Dept Name from Profit and Loss Detail whenever a budget holder asks in the channel. | No monthly report pack wait |
| Who sees which QuickBooks data | A full export shared in a Teams chat exposes every account, customer and vendor to everyone in it. | Attach only the datasets the agent's audience should see, and exclude or hash customer columns in the source. | Finance controls the scope |
| Triggering a lookup | Microsoft 365 Copilot has no link to your books, so a cash question gets a generic reply or a request for a file. | A server description naming balance sheet, deposits and profit and loss tells the agent when to call Dataddo. | Answers from your books |
| Forecast code and the ledger | Analysts copy account names from a ledger export into forecast code and fix mismatches by hand later. | GitHub Copilot in VS Code describes Transaction Lines Report V2 and samples real Section values through .vscode/mcp.json. | One set of account names |
| Token consumption | Copilot spends tokens exploring raw QuickBooks 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 QuickBooks 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 the schedule you set, for example daily. The QuickBooks API returns up to 1,000 rows per batch, so larger histories are loaded in multiple batches with a data backfill.
QuickBooks 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 QuickBooks datasets such as Balance Sheets V2, Deposits and Profit and Loss Detail with Dataddo and attach them to a Copilot destination or AI Model. Then add the Dataddo Data Access MCP tool (https://headless.dataddo.com/mcp-data) to a Copilot Studio agent, authenticate with OAuth 2.0 Dynamic discovery and publish it to Teams.
No. The agent reads QuickBooks data that Dataddo has already extracted, through the Data Access MCP server. Attach only the datasets the agent's audience should see, for example deposits and department results.
Write a specific server description in Copilot Studio, for example accounting data from QuickBooks: balance sheet, deposits, profit and loss. The agent uses it to decide when to call Dataddo.
Publish the Copilot Studio agent, then add it through Channels > Teams and Microsoft Copilot. Users type @ and select the agent in Teams or Microsoft 365 Copilot to ask their question.
Yes. Add the Dataddo server to .vscode/mcp.json with type http and the URL, start it, sign in and use Copilot Chat in Agent mode. Business and Enterprise orgs must enable the MCP servers in Copilot policy.
The QuickBooks API returns up to 1,000 rows per batch, and date-range datasets only cover their window. Load larger or older histories in batches with a full data re-sync, then ask again.
No. The agent queries extracted QuickBooks entities through the Dataddo semantic layer. It cannot create, edit or send invoices, and Dataddo never accepts SQL from the model.