Outlook AI: not just smart reading, but taking action in your ERP
Outlook AI is an Outlook add-in that allows you to send emails and attachments directly to custom-made AI agents. Where tools like Copilot and ChatGPT stop at summarizing, Outlook AI goes further: through tool calling, the agent triggers data flows that have been running at clients for years, executing actions directly in ERP systems such as Exact Synergy, AFAS, and Business Central. Think of creating documents, registering service requests, or processing expense claims — all from within Outlook, without copy-pasting. The difference: not an assistant that talks, but an assistant that acts.
Robert Keunen
4 min
Summarizing emails with AI? Anyone can do that by now. Copilot does it, ChatGPT does it, and new tools appear every month. Summarizing, querying, analyzing — it has become a commodity. The question is: what is the next step? Because that is where the real work lies. After all, after reading, someone still has to transfer the action items to the ERP system.
Creating a document in Synergy. Registering a service request in AFAS. Updating a status in Business Central.
That final piece — taking action — is where every generic AI tool stops. And that is exactly where Outlook AI begins.
The bridge that an LLM lacks
A language model can summarize a meeting report perfectly fine. But it cannot log into your Exact Synergy environment and create a document with the correct metadata, type, and status. That requires a structured connection to your ERP — and that connection does not exist in ChatGPT or Copilot. At Any2Info, we have been building data flows for years: structured connections that read from and write to ERP systems like Exact Synergy, AFAS, and Business Central. Hundreds of these data flows run daily for our clients. They form the reliable bridge between business processes and business systems. With the introduction of tool calling, we are now making those same data flows available to AI agents. An agent can call a data flow via a tool call and actually execute an action in your ERP. Simply with a (voice) command such as: “Create a new document in Synergy based on the summary and action items.” That is the difference between an assistant that talks and an assistant that acts.
How this works in practice
Let's take a concrete example. A sales manager receives weekly visit reports from five field sales representatives — as Word or PDF attachments via email. With Outlook AI, the process works as follows:
• Select the emails — the manager selects all five emails with visit reports in Outlook.
• Choose the agent — in the Outlook AI panel, they choose “Exact SynergyDocs AI.”
• Chat with the agent — the AI reads all attachments and presents an overview: findings, action items, and points of attention per representative.
• Give the instruction — “Create a new Synergy document with the summary and action items.” Through tool calling, the agent calls a data flow that creates the document in Exact Synergy — with the correct content, metadata, and status.
Up to this point, steps 1 through 3 are what any AI tool can do. Step 4 is what is only possible when you have already built the bridge to your ERP. And we have that bridge. The result: an approved document in Synergy, ready for follow-up. Five minutes instead of ninety. No copy-pasting, no manual input, no more switching between systems.
One approach, dozens of applications
Because each agent has its own prompts, parameters, and tool calls, the same approach applies to virtually any situation where email drives an ERP action:
• Service requests — a customer emails about a malfunction, the agent creates a service ticket in your ERP.
• Quotation requests — the agent extracts specifications from an RFQ and drafts a draft quotation.
• Expense claims — employees send receipts via email (including images, PDF), the agent categorizes and registers them.
• Onboarding — HR receives documents from new employees, the agent checks for completeness and records everything.
Each case combines the same building blocks: an AI agent that understands, and data flows that execute. The intelligence is in the model. The action is in the data flow. Outlook AI brings them together.
Not just another AI tool, but an executive assistant
Let's be honest: the market doesn't need another tool that summarizes emails. What organizations need is an AI that doesn't stop at understanding, but pushes through into the business system. With the correct permissions, within the right workflows, and with a full audit trail. That is what Outlook AI delivers. Not because we have the smartest language model — we don't, we leave that to OpenAI and Anthropic. But because we already have the integration to your ERP. And that integration turns a smart model into an executive assistant.