Starting point
Sales & quotes
Follow up on open quotes automatically
Every quote that stays unanswered is followed up automatically, at the agreed interval and in the same conversation as the quote itself. The process builds on the environment already in place – Microsoft 365, Google Workspace or a self-hosted ERP – and sales only decides the exceptions.
Process architecture
From a silent quote to a documented follow-up.
The process reads the stock of open quotes from the company's leading system and checks for each case whether and how to follow up. Drafting, sending and logging run on the services the company already uses – in a Microsoft, a Google or a self-hosted environment. People step in where a rule does not apply.
01Input
Open quotes and their context come together.
The process starts with silence rather than a message: a quote that has had no answer for days. The leading system supplies the quote, its deadline and the contact, together with the correspondence already attached to the case.
2 Steps
02Process
The right message is derived from the state of the case.
The draft comes from the quote itself, not from a template full of placeholders. The rules then check whether a follow-up is allowed at all; anything outside the agreed frame goes to a salesperson.
4 Steps
03Output
The message goes out and the case stays traceable.
The follow-up sits in the same conversation as the quote, sales sees the current state without asking, and every attempt is documented on the case.
3 Steps
Source01Detect the open quote
A scheduled run checks daily which quotes have passed the agreed deadline without a reply – through Microsoft Power Automate, Google Apps Script or n8n, depending on the environment.Details
Detect the open quote
A scheduled run checks daily which quotes have passed the agreed deadline without a reply – through Microsoft Power Automate, Google Apps Script or n8n, depending on the environment.
Interfaces
- Microsoft Graph API
- SharePoint API
Next steps
- Load customer and history
Data02Load customer and history
Contact, quoted items and previous correspondence come together, through the Microsoft Graph API, the Gmail API, or a database view and IMAP on the company's own servers.Details
Load customer and history
Contact, quoted items and previous correspondence come together, through the Microsoft Graph API, the Gmail API, or a database view and IMAP on the company's own servers.
Interfaces
- Azure AI Document Intelligence
- Mistral OCR
- Dataverse API
Next steps
- Draft the follow-up
Action03Draft the follow-up
A language model turns quote and history into a short, factual draft: Azure OpenAI Service, Google Cloud Vertex AI, or a model served through Ollama in the company's own data centre.Details
Draft the follow-up
A language model turns quote and history into a short, factual draft: Azure OpenAI Service, Google Cloud Vertex AI, or a model served through Ollama in the company's own data centre.
Interfaces
- Power Automate
- Azure Functions
- Microsoft Graph API
Next steps
- Check follow-up rules
Decision04Check follow-up rules
The rules check attempts, minimum interval, hold flag, order value and overdue invoices, then decide between sending and escalating to sales.Details
Check follow-up rules
The rules check attempts, minimum interval, hold flag, order value and overdue invoices, then decide between sending and escalating to sales.
Interfaces
- Azure OpenAI GPT
- Anthropic Claude
- AI Builder
Next steps
- Send the follow-upstandard case
- Take over personallyexception
Approval05Take over personally
If the case falls outside the frame – a large order, an ongoing negotiation, a complaint – it reaches the responsible salesperson with the draft, via a Microsoft Teams Adaptive Card, Google Chat or the company's own channel.Details
Take over personally
If the case falls outside the frame – a large order, an ongoing negotiation, a complaint – it reaches the responsible salesperson with the draft, via a Microsoft Teams Adaptive Card, Google Chat or the company's own channel.
Interfaces
- Teams Adaptive Cards
- Power Apps
Next steps
- Send the follow-upafter approval
System06Send the follow-up
Sending runs through Microsoft Outlook, Gmail or the company's own mail server via SMTP – always from the responsible salesperson's address and inside the quote's reply thread.Details
Send the follow-up
Sending runs through Microsoft Outlook, Gmail or the company's own mail server via SMTP – always from the responsible salesperson's address and inside the quote's reply thread.
Interfaces
- Dynamics 365 API
- Azure Service Bus
Next steps
- Document the dispatch
- Inform sales
Result07Document the dispatch
The activity is recorded on the quote with timestamp, attempt number and the wording sent – through the Dynamics 365 Sales API, the Google Sheets API or the Odoo External API.Details
Document the dispatch
The activity is recorded on the quote with timestamp, attempt number and the wording sent – through the Dynamics 365 Sales API, the Google Sheets API or the Odoo External API.
Interfaces
- Power BI API
- Teams Webhook
Next steps
- Set the next reminder
Result08Inform sales
The responsible salesperson receives a short note on the current state, collected at the end of the run rather than per single case.Details
Inform sales
The responsible salesperson receives a short note on the current state, collected at the end of the run rather than per single case.
Interfaces
- Power BI API
- Teams Webhook
Result09Set the next reminder
The next contact is scheduled on the case or in the calendar; after the final attempt the quote is closed with a reason.Details
Set the next reminder
The next contact is scheduled on the case or in the calendar; after the final attempt the quote is closed with a reason.
Interfaces
- Power BI API
- Teams Webhook
System landscape
The same process in three environments.
- Microsoft
Microsoft Graph API
Möglicher Baustein für die Microsoft-Systemvariante.
- Microsoft
SharePoint API
Möglicher Baustein für die Microsoft-Systemvariante.
- Microsoft
Azure AI Document Intelligence
Möglicher Baustein für die Microsoft-Systemvariante.
- Microsoft
Mistral OCR
Möglicher Baustein für die Microsoft-Systemvariante.
- Microsoft
Dataverse API
Möglicher Baustein für die Microsoft-Systemvariante.
- Microsoft
Power Automate
Möglicher Baustein für die Microsoft-Systemvariante.
- Microsoft
Azure Functions
Möglicher Baustein für die Microsoft-Systemvariante.
- Microsoft
Azure OpenAI GPT
Möglicher Baustein für die Microsoft-Systemvariante.
- Microsoft
Anthropic Claude
Möglicher Baustein für die Microsoft-Systemvariante.
- Microsoft
AI Builder
Möglicher Baustein für die Microsoft-Systemvariante.
- Microsoft
Teams Adaptive Cards
Möglicher Baustein für die Microsoft-Systemvariante.
- Microsoft
Power Apps
Möglicher Baustein für die Microsoft-Systemvariante.
- Microsoft
Dynamics 365 API
Möglicher Baustein für die Microsoft-Systemvariante.
- Microsoft
Azure Service Bus
Möglicher Baustein für die Microsoft-Systemvariante.
- Microsoft
Power BI API
Möglicher Baustein für die Microsoft-Systemvariante.
- Microsoft
Teams Webhook
Möglicher Baustein für die Microsoft-Systemvariante.
- Interfaces in use
Microsoft Dynamics 365 Sales API
Microsoft environment: reads open quotes with deadline and owner and writes every follow-up activity back to the case.
- Interfaces in use
Gmail API
Google environment: retrieves the history for the quote and sends the follow-up inside the existing reply thread.
- Interfaces in use
Google Sheets API
Google environment: reads the maintained quote list with deadline and owner and writes every attempt back.
- Interfaces in use
Odoo External API
Individual environment: reads open quotes from the self-hosted ERP and records every activity there.
- Interfaces in use
SMTP und IMAP
Individual environment: sending through the company's own mail server and reading the thread for the specific case.
- Interfaces in use
Azure OpenAI Service
Drafts the message in the Microsoft environment, operated in a European region.
- Interfaces in use
Google Cloud Vertex AI
Drafts the message in the Google environment, operated in a European region.
- Interfaces in use
Ollama
Drafts the message inside the company's own data centre when quote data must not leave the building.
- Interfaces in use
n8n
Visible orchestration with schedule, retry and logging for the self-hosted variant.
- Possible apps & platforms
Microsoft Dynamics 365 Sales
Leading system for quotes, deadlines and ownership in the Microsoft environment.
- Possible apps & platforms
Microsoft Outlook und Microsoft Teams
Sending channel and place of exceptions in the Microsoft environment.
- Possible apps & platforms
Google Sheets und Gmail
Maintained quote list and sending channel in the Google environment.
- Possible apps & platforms
Google Chat
Place of exceptions and the daily summary in the Google environment.
- Possible apps & platforms
Odoo
Leading system for quotes, orders and overdue invoices in the self-hosted environment.
- Possible apps & platforms
Grafana
Overview of throughput, backlog and failed attempts along the chain.
Implementation in context
What the process does and what it deliberately leaves to people.
The process covers only the time after the quote has been sent. It does not create quotes, does not change prices and does not negotiate. What it does is the part that gets forgotten today: reminding a customer, factually and on time, about an open quote.
The environment determines the tools, not the process. In a Microsoft 365 environment sales data comes from Dynamics 365 and sending from Outlook; in a Google Workspace environment the maintained quote list and Gmail are enough; in a self-hosted environment the process reads the company's own ERP and sends through its own mail server. Which variant fits is decided at the start and stays the same for all cases.
The decision logic is deliberately narrow. A message goes out only when deadline, minimum interval, attempt count and the absence of a hold flag all fit. Every other case – a quote above a defined amount, an ongoing negotiation, a customer with overdue invoices – goes to the responsible salesperson, not to the customer.
Personal data stays inside the company's own environment. What is read is the contact data and the correspondence for that specific case, not the whole mailbox; permissions are limited to this purpose and can be revoked. If even the draft must not leave the building, the language model runs in the company's own data centre. Every draft and every dispatch is logged with timestamp and trigger.
Target picture
Every open quote has a defined follow-up path that works without a person remembering it. Sales can see which quotes are still alive and is only needed where a decision is due. What remains on each quote is a traceable series of attempts instead of an assumption.
Expected benefits
- Open quotes are followed up evenly, no matter how full the calendar of the responsible salesperson is.
- The follow-up reaches the customer in the reply thread of the quote and therefore reads as a continuation of the conversation, not as a bulk mail.
- The process adapts to the existing environment instead of making a system change a precondition.
- Sales spends its time on cases where a decision is due instead of maintaining reminder lists.
- For every quote it is traceable when and with which wording a follow-up was sent – even across holidays or staff changes.
- Quotes without any reaction are closed cleanly after the final attempt, so the pipeline shows the real state.
Prerequisites to start
- 01Quotes are kept in one place – CRM, ERP or a binding list – with a sending date and a responsible person.
- 02A mailbox or delegated access that may send on behalf of the responsible salesperson.
- 03A written rule stating after how many days, how often and up to which order value automatic follow-ups are allowed.
- 04Maintained contact data on the quote; a quote without a reachable contact goes straight into the exception path.
- 05A decision on the environment: Microsoft 365, Google Workspace or self-hosted – and the matching access rights.
More use cases
Matching solutions from your industry
Email & intake channels
Understand and route incoming messages automatically
AI identifies requests, attachments and priorities, then moves every message into the right downstream workflow with clear controls.
Faster response times, consistent ownership and a traceable status from the first customer contact.
- Microsoft Graph / Gmail API
- CRM- oder Ticket-API
- Webhook / REST
- Outlook & Microsoft Teams
Sales & quoting
Turn customer inquiries into finished quotes automatically
Every customer inquiry from the shared mailbox and the web form is extracted, priced against the item master and the agreed terms, and sent as a complete quote. Only unmatched lines or discounts outside the rules reach inside sales; everything else leaves the company the same day.
Every inquiry leads to a complete quote with a number, line items and a validity period on the same day. Inside sales only decides where the match is missing or the price leaves the agreed rules, and each of those decisions stays on the case with its basis.
- Microsoft Graph / Gmail API
- Azure AI Document Intelligence / Google Document AI
- Azure OpenAI Service / Vertex AI / Ollama
- ERP REST / OData / Google Sheets API
Accounting & invoicing
Create and send compliant e-invoices automatically
Every approved outgoing invoice is turned into a structured e-invoice in XRechnung or ZUGFeRD format, checked for mandatory data and sent over the agreed channel. Only invoices with incomplete or conflicting details reach the accounting team first; everything else leaves the company in the same run.
Every approved invoice is created, checked and sent as a compliant e-invoice over the agreed channel in the same run. Accounting only corrects incomplete or conflicting details, and every sent version is archived audit-safe together with its proof of sending.
- REST API
- ZUGFeRD und XRechnung
- Microsoft Graph API
- Gmail API
Finance and receivables
Send payment reminders from overdue invoices automatically
Every overdue open item from Microsoft Dynamics 365 Business Central, DATEV or the line-of-business system is checked against due date, grace period and reminder level and sent as a payment reminder through Microsoft Outlook or Gmail. Only blocked customers, missing recipients and amounts outside the agreed level go to finance; everything else leaves the same day.
Every overdue open item receives the next allowed reminder from the stored template as soon as due date and grace period are met. Only blocked customers, missing recipient addresses and amounts outside the agreed level reach finance as a case ready for a decision. Send, reminder level and record sit in the system of record, not in a private list.
- Microsoft Graph API
- Gmail API
- REST API
- Webhook
Finance & documents
Validate and post incoming invoices
Invoices are captured, validated and moved through approval, accounting and archiving with explicit exception controls.
Fewer capture errors, clear validation steps and an auditable path from document to accounting entry.
- ERP REST / OData / IDoc
- E-Mail, Peppol oder Upload
- DMS- und Archiv-API
- Azure AI Document Intelligence
Finance and receipts
Automatically file expenses from receipt photos
Every receipt photo from Microsoft Outlook, Gmail or the line-of-business mailbox is read, checked against travel policy and submitted as a reimbursement claim in the system of record. Only unreadable shots and amounts outside the agreed limits go to a person; everything else is ready for a decision the same day.
Every receipt has an owner, a cost centre and a visible status. Inside policy the claim is created without retyping. Exceptions sit with the person who may decide, together with the image and the rule that was applied.
- Microsoft Graph API
- Gmail API
- REST API
- Azure AI Document Intelligence
Your next step
Which process costs your team unnecessary time every day?
Give us a short outline. We will tell you honestly where automation is useful—and where it is not.
