Data to AI™ / Copilot/Sage Accounting
Give finance and sales a Teams agent that answers who owes what in Sage, which suppliers are due and how ledger accounts are trending.
Less tokens, better answers.
Microsoft 365 Copilot
Which customers still owe us for invoices that fell due in September?
Three customers still owe £18,450 on September invoices. Harlow Interiors accounts for about half of it, on an invoice due 4 Sep.
| Contact name | Total amount | Outstanding amount | Due date |
|---|---|---|---|
| Harlow Interiors Sales Invoices No Lines | £14,600 | £9,200 | 4 Sep |
| Brightwell Studio Sales Invoices No Lines | £7,900 | £5,350 | 12 Sep |
| Penrose Catering Sales Invoices No Lines | £4,100 | £3,900 | 19 Sep |
Read from Sales Invoices No Lines, one row per invoice, so totals are not repeated for every invoice line.
Sage Accounting, formerly Sage One, is cloud accounting software for small businesses. Dataddo extracts sales and purchase invoices, transactions, journals, ledger accounts, contacts and the product and service catalogues.
@Sage Finance Is this customer over its Credit limit? Show Balance, Credit limit and the open Sales Invoices No Lines behind it.
Sales posts the question in the channel before confirming a large order. The account manager and credit controller agree on the reply in the same thread.
@Sage Finance Summarise Purchase Invoices due before month end by Contact name, with Outstanding amount and Due date, for the payment approval meeting.
Before the weekly meeting, the finance lead asks Microsoft 365 Copilot for supplier bills due and pastes the grouped list into the meeting notes.
Use the dataddo tools to describe Ledger Accounts and list every Nominal Code with Name and Ledger Account Type Displayed As as JSON.
A finance engineer uses GitHub Copilot in VS Code to keep the cash forecast mapping aligned with the current chart of accounts in Sage.
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 the question gets asked | Sales emails finance, finance opens Sage, copies the customer balance into a reply, and the order waits in between. | The Sage agent answers in the Teams channel where sales and finance already discuss the order. | Answers inside the thread |
| When the agent calls Sage | A general assistant has no idea which system holds receivables and answers from whatever document it finds. | The server description you write in Copilot Studio tells the agent to call Dataddo for Sage invoices, suppliers and ledger questions. | Finance questions routed correctly |
| Ledger account meaning | A Nominal Code in a spreadsheet says nothing about whether it is income, expense or a balance sheet account. | Ledger Accounts carries the type, group and classification next to each code, with field descriptions from the semantic layer. | Codes the agent can read |
| Token consumption | Copilot spends tokens exploring raw Sage Accounting 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 Sage Accounting 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. Every Sage Accounting dataset re-reads a relative date window on each run, so older history needs a one-time full data re-sync.
Sage Accounting 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 Sage Accounting source in Dataddo with Sales Invoices No Lines, Purchase Invoices and Ledger Accounts, and attach it to a Copilot destination or AI Model. In Copilot Studio, add the Model Context Protocol tool https://headless.dataddo.com/mcp-data with OAuth 2.0 Dynamic discovery, then publish the agent to Microsoft 365 Copilot and Teams.
The server description you write in Copilot Studio tells the agent when to call Dataddo. Describe it as the source for Sage invoices, suppliers and ledger data so finance questions trigger a lookup.
Yes. Publish it through Channels > Teams and Microsoft Copilot. Users then type @ and pick the agent in either app, and both read the same Sage flows.
At least admin-level permissions in Sage, and the business must belong to the country you select during authorization. A Sage developer account is not linked to a business and cannot be used.
Yes. Add the server to .vscode/mcp.json, start it, sign in and use Copilot Chat in Agent mode. On Business and Enterprise an admin must enable the MCP servers in Copilot policy.
Yes. Untick Contacts fields such as Bank account - number and Bank account - IBAN when you create the source, or hash them with md5 or xxh3 before they reach the flow.