Power Automate and AI Builder – process automation using artificial intelligence

Training process

Training needs analysis

If you have specific requirements regarding the training programme, we will carry out a training needs analysis for you. This will guide us on which aspects of the programme should receive greater emphasis, so that the training programme meets your specific needs.

What will you gain?

Build flows on your own - You will learn how to create automated, instant, and scheduled flows yourself, so you can streamline everyday tasks faster without relying on IT for each small automation.

Connect Microsoft 365 tools - After the training, you will link Outlook, SharePoint, Teams, Forms, Excel, and Dataverse into one process, so data and alerts move between apps without manual copying.

Handle data with confidence - You will master IF conditions, switches, array actions, OData filters, and JSON parsing, so you can build flows that respond correctly to different data scenarios.

Use AI Builder effectively - You will learn how to apply AI Builder models for document reading, content classification, and prediction, so you can automate tasks that used to require manual review.

Automate document workflows - You will practice the full process from collecting a document to saving structured data, helping you reduce handling time for invoices, requests, reports, and similar files.

Make data-driven decisions - You will learn how to run prediction models and use their results inside flows, so you can route cases, escalate requests, or support operational decisions automatically.

Reduce errors and rework - You will learn practical design, testing, and monitoring techniques, so you can avoid common flow issues, connector limit problems, and solutions that are hard to maintain.

Run flows from mobile devices - You will see how to trigger instant flows from a phone, Teams, or Power Apps, so you can enable fast reporting, requests, and process handling even when you are away from the desk.

Training programme

1. Introduction to Power Automate

what Power Automate is – types of flows (automated, manual, scheduled),
user interface: environments, connectors, licenses,
best practices in flow design,
security and permissions principles.

2. Building the first flows

automatic flows (Automated Cloud Flows),
triggers: Outlook, SharePoint, Teams, Forms, Dataverse,
typical scenarios:
- automatic saving of attachments,
- notifications in Teams,
- updating lists/files upon the arrival of new data.
manual flows (Instant Flows):
- flows launched from a phone or Teams/Power Apps,
- scenarios: quick reporting, submissions, registers,
recurring flows (Scheduled Flows):
- status monitoring, weekly summaries, automatic reminders.

3. Working with data and conditions

IF conditions, parallel branches, switches (Switch),
operations on arrays and records,
OData filters in practice,
JSON parsing – when and how to use it,
dynamic creation of e-mail/SMS/notification content.

4. Advanced connectors and integrations

SharePoint – lists, libraries, permissions,
Outlook – automatic correspondence workflow,
Teams – working in channels, creating tasks, notifications,
Forms – form processing,
Excel Online – pitfalls of working with tables and large volumes of data,
Power Apps – flows as application logic.

5. AI Builder in practice

AI Builder basics,
- types of models and their applications,
- Form Processing – reading data from documents,
- Prediction – predictive models (e.g. risk, result),
- Classification – categorization of text/documents,
- Object Detection – detecting objects in photos,
- Document Automation – automatic document processing,
- licensing requirements and AI credit limits.

6. Workshop: creating AI Builder models

Model 1: Document Processing (Form Processing),
- training the model on invoices/applications/reports (depending on the client's materials),
- testing the model and evaluating the quality of predictions,
- generating output data for Power Automate,
Model 2: Text Classification (Category Classification),
- developing categories and labels,
- training on the client's examples (optional),
- implementing automatic labels in flows,
Model 3: Prediction (Prediction),
- creating a simple model predicting the result/submission/status,
- interpreting quality indicators.

7. Integration of AI Builder with Power Automate

triggering the AI model in the flow,
retrieving and saving prediction results,
creating processes of the „document automation” type – from retrieving the document to saving structured data,
automatic categorization of emails/tickets,
automatic decision-making based on predictions (routing, approval, escalation).

8. The most common mistakes and good practices

how to optimize flows,
how to avoid errors related to connector limits,
how to design scalable automations for the entire organization,
how to test and monitor the operation of flows,
principles of version control and documentation.

What are the prerequisites for participating in the training?

Basic Microsoft 365 skills - You should be comfortable using Outlook, Teams, SharePoint, or Excel Online, so during the exercises you can focus on automation instead of learning the tools themselves.

Understanding office processes - You should understand how common business processes work, such as document handling, requests, or approvals, so you can design flows that make practical sense.

Basic data handling - You should understand terms such as record, table, column, and filter, because you will work with lists, forms, and input data used later in AI models.

Readiness for hands-on work - You should be ready to complete exercises on your own computer and test your own scenarios, because the training is based on practical flow and model building.