Data Alchemy — Software IDP con AI
ERP Integration

TeamSystem Integration: document data written straight into TeamSystem

With Data Alchemy, invoices, delivery notes and orders reach TeamSystem already read by the AI and checked against your master data, with no manual data entry. Your users keep working in TeamSystem and only review the exceptions that are flagged.

99.8%Accuracy with Claude
~12 sPer 1-page document (Claude Sonnet)
AI agentor REST API into TeamSystem
0Manual data entry
Context

Why integrate TeamSystem with an IDP engine

TeamSystem is one of the most widely used management systems among Italian companies, but the accounts-payable cycle still requires manually entering invoices, delivery notes and orders. Every document is read and typed into TeamSystem by hand, with errors, delays and reconciliations slowing down the back office.

Data Alchemy's TeamSystem integration removes that work: the Intelligent Document Processing (IDP) engine, software that reads documents with AI and extracts structured data, reads the document, extracts the fields, checks them against TeamSystem master data (vendors, items, terms) and writes the record straight into the system, ready to be posted.

This direct link between Data Alchemy and your system is what we mean by native integration: the full explanation, including the available connection methods, is on the dedicated page.

How it connects

Supported TeamSystem integration methods

Extracted data reaches TeamSystem in one of two ways: through the AI agent, installed at your premises, or, if you develop in-house, through an integration on Data Alchemy's REST API and webhooks, included in every licence.

AI agent

The AI agent is installed at your premises: it connects to Data Alchemy over websocket and APIs and posts the extracted data into TeamSystem, including orders with header and lines, on the destination configured from a graphical interface — a database, CSV, JSON or TXT files, or APIs — with no connectors to build. Your TeamSystem credentials stay in the agent, in your perimeter. It is included in the Enterprise licence and available as a separately quoted add-on on Business.

Data Alchemy REST API and webhooks

For developers: submit documents through the REST API and receive the structured JSON via webhook, signed with HMAC SHA-256, or with a GET. Your own integration handles the write into TeamSystem.

Mail service for acquisition

From the Business licence, the Mail service installed on your premises picks up documents from your company mailboxes and brings them into Data Alchemy: invoices, delivery notes and orders enter the flow with no manual uploads.

Validation on TeamSystem master data

Before writing, data is matched against TeamSystem master data — vendors, item codes, open orders. This is done by remote validation, which checks individual values against master data (for example that an item code exists, or the vendor code found from the VAT number), and by external fields, which compare the document with the data it refers to (for example the purchase order quoted on a delivery note). Both are included from the Business licence.

Data flow

From document to TeamSystem in four steps

The same flow applies to invoices, delivery notes, orders, contracts and price lists: the document goes in, structured data comes out inside TeamSystem.

01

Acquisition

The document arrives via email (business mailboxes, via the on-premise Mail service, from the Business licence), upload or a monitored folder.

02

AI extraction

An LLM dedicated to the document model extracts the fields, with no templates or per-layout rules.

03

Validation

Data is validated and enriched against TeamSystem master data, with anomalies flagged for review.

04

Write to TeamSystem

Validated data reaches TeamSystem through the AI agent installed at your premises (database, files or APIs) or through your own integration on the REST API, ready to be posted.

Benefits

What changes with Data Alchemy's TeamSystem integration

Zero data entry

Data enters TeamSystem with no manual typing: the finance team moves from copying to reviewing exceptions.

Master-data consistency

Validation against TeamSystem master data reduces coding errors, wrong vendors and items not found.

Faster closing times

Payables reach TeamSystem with no manual data entry, speeding up posting, control and payment.

No new software for users

Users keep working in TeamSystem: the automation operates behind the scenes on document acquisition.

Full traceability

Every document keeps the link to the TeamSystem record it created, for audit and reconciliation.

Scales to all documents

From invoice to delivery note to order: the same TeamSystem integration covers every document flow.

FAQ

Frequently asked questions about TeamSystem integration

Yes. Data extracted from documents reaches TeamSystem through the AI agent installed at your premises (a database, CSV, JSON or TXT files, or APIs) or through an integration you build on Data Alchemy's REST API and webhooks, mapped to invoice, order and delivery-note fields, after validation against TeamSystem master data.
The integration feeds TeamSystem's accounts-payable and management flows through the AI agent installed at your premises (a database, CSV, JSON or TXT files, or APIs) or Data Alchemy's REST API, adapting to your environment's configuration.
Accounts-payable invoices, delivery notes, orders, contracts and price lists. The same Intelligent Document Processing flow extracts the data and writes it into TeamSystem, regardless of document type.
Before writing, data is matched against TeamSystem master data — vendors, item codes, open orders. Anomalies are flagged for review, so only consistent data is entered.
With Claude Sonnet or higher, reading takes on average around 12 seconds for a one-page document and around 18 seconds for two pages; the write to TeamSystem happens straight after validation, through the AI agent or your own API integration.

Get your documents into TeamSystem, without data entry

Show us a sample of your documents: we'll demonstrate extraction, master-data validation and the write to TeamSystem on your real case.

Plan a call with a demo on your own documents