Data to AI™ / Copilot/Xero

Xero to Microsoft Copilot integration

Put a Xero agent in Teams so department heads can check spend, cash and receivables themselves instead of waiting for the monthly finance pack.

Less tokens, better answers.

  • Lower AI costs for the same work
  • More accurate, reliable answers
  • Read-only
  • Uses the Xero data you already sync
  • SOC 2 Type II certified
Microsoft 365 Copilot
Connected to Dataddo

How much cash came in and went out of each bank account in September?

Copilot Answer · Xero

September closed with a net inflow of $9,350: $89,600 Cash Received against $80,250 Cash Spent. The Business Account carried most of both.

Bank AccountCash ReceivedCash SpentClosing Balance
Business Account Reports - Bank summary $84,200$71,650$52,900
Business Savings Reports - Bank summary $5,400$0$40,000
Company Credit Card Reports - Bank summary $0$8,600-$3,150

Taken from the Bank summary report for one Date Start to Date Stop period, not rebuilt by adding up Bank Transactions.

source
Xero · as of Mon 06:40 UTC
covers
1-30 Sep 2026
Example answer · fictional account and figures
Xero in Copilot

Questions Copilot can answer from your Xero data

Xero is cloud accounting software for small and medium-sized businesses. Dataddo extracts invoices, payments and bank transactions as well as Xero reports such as Aged Receivables, Bank summary, Profit and Loss and Budget summary.

Department spend in Teams

Ask Copilot

@Xero Ledger What did Marketing spend last month? Use Profit and Loss by Tracking Category and compare it with Reports - Budget summary.

Budget holders ask the agent in their own Teams channel instead of emailing finance, and see actuals per tracking category against the budget they own.

Monday cash update

Ask Copilot

@Xero Ledger Give me Cash Received, Cash Spent and Closing Balance per Bank Account from Reports - Bank summary for last week.

The treasurer asks Microsoft 365 Copilot on Monday morning and pastes the answer into the weekly cash update for leadership.

Chart of accounts in VS Code

Ask Copilot

Use the dataddo tools to query Accounts and return Code, Name, Type and Reporting Code as JSON for our chart-of-accounts seed.

A finance systems developer uses GitHub Copilot in Agent mode to keep internal reporting mappings in line with the accounts finance adds in Xero.

Xero datasets you can use in Copilot →
Pricing

Free during private pre-release.

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.

Data to AITM

Serve governed business data to Claude, ChatGPT and other AI tools over MCP.

Private pre-release

Free during pre-release

Enterprise

Flexibly deploy Dataddo in any cloud or hybrid environment.

Custom

We have a payment model that works for you

See all plans and features →
With vs. without

Xero in Copilot, with and without Dataddo

Without Dataddo With Dataddo Outcome for you
Budget holders asking about spend Department heads email finance for their numbers, then wait for the monthly pack to see actuals against budget. The Xero agent in their Teams channel reads Profit and Loss by Tracking Category and answers per Tracking Category Name. Self-serve spend checks
Routing questions to Xero Copilot has no link to Xero, so finance questions get answers from documents rather than the ledger. The server description in Copilot Studio tells the agent to call Dataddo for Xero invoices, cash, budgets and tracking categories. Xero questions reach Xero
Chart of accounts in code Mapping files in the reporting repository drift as accountants add or archive account codes in Xero. GitHub Copilot in Agent mode reads Accounts through the server in .vscode/mcp.json, so mapping updates start from current codes. Mappings match the ledger
Token consumption Copilot spends tokens exploring raw Xero 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
Datasets

Xero datasets you can use in Copilot

The Xero 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

Account IDAccountID
string
CodeCode
string
NameName
string
TypeType
string
Tax TypeTaxType
string
Enable Payments To AccountEnablePaymentsToAccount
float
Bank Account NumberBankAccountNumber
string
Bank Account TypeBankAccountType
string
Currency CodeCurrencyCode
string
Reporting CodeReportingCode
string
Reporting Code NameReportingCodeName
string
Account StatusStatus
string
DescriptionDescription
string
XeroTenantID
string

Need a dataset, metric, or attribute you don't see?

Tell us what's missing and we'll add it to the connector.

Request it

Runs on your schedule, for example daily. Datasets with a date range, such as Invoices and Profit and Loss, re-read a sliding window, so older history needs a one-time full data re-sync. Contacts and Accounts pull all current records.

Xero connector →
Benchmark

More right answers. Half the confident mistakes.

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.

78.5%

of questions answered correctly - the best of the four delivery methods tested

2x

fewer confidently wrong answers - 14.0% of runs against 24.0% and 26.3%

2.8x

more correct answers on messy CRM data - better on 8 questions, worse on none

Answered correctly All 43 questions - higher is better
Wrong, but stated as fact Share of runs - lower is better

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 →
FAQ

Xero and Copilot: FAQ

How do I connect Xero to Copilot?

Create a Xero source in Dataddo with Reports - Bank summary, Profit and Loss by Tracking Category and Invoices, and attach it to a Copilot destination or AI Model. In Copilot Studio, add https://headless.dataddo.com/mcp-data as a Model Context Protocol tool with OAuth 2.0 Dynamic discovery and publish to Teams and Microsoft 365 Copilot.

How do I add Xero data to a Copilot Studio agent?

In the agent, go to Tools > Add a tool > New tool > Model Context Protocol, enter the Dataddo URL, choose OAuth 2.0 with Dynamic discovery and sign in with the Dataddo account that holds the Xero flow.

Which Xero questions will the agent route to Dataddo?

Those that match the server description you set in Copilot Studio. Mention Xero invoices, cash, budgets and tracking categories there so the agent calls Dataddo for them.

Can department heads see spend by cost centre?

Yes, if you use Xero tracking categories. Profit and Loss by Tracking Category and Journals with Tracking carry Tracking Category Name, so the agent can answer per department.

Does the agent work in Microsoft 365 Copilot as well as Teams?

Yes. Publish through Channels > Teams and Microsoft Copilot. In both, users type @ and select the agent, and it reads the same Xero data.

Can GitHub Copilot query Xero in VS Code?

Yes. Add the server to .vscode/mcp.json with type http and the URL, start it and sign in. Business and Enterprise organizations must enable the MCP servers in Copilot policy first.