{"id":4992,"date":"2021-03-09T08:00:00","date_gmt":"2021-03-09T16:00:00","guid":{"rendered":""},"modified":"2025-06-11T07:55:17","modified_gmt":"2025-06-11T14:55:17","slug":"how-to-implement-document-automation-in-your-business-with-microsoft-power-platform","status":"publish","type":"post","link":"https:\/\/cm-edgetun.pages.dev\/en-us\/power-platform\/blog\/power-automate\/how-to-implement-document-automation-in-your-business-with-microsoft-power-platform\/","title":{"rendered":"How to implement document automation in your business with Microsoft Power Platform"},"content":{"rendered":"

Thanks to automation solutions and AI, organizations can accelerate and optimize the processing of documents so humans can be freed from performing repetitive, low value and error prone tasks. This applies to any kind of printed or digital form like account payable invoices, delivery orders, receipts, and more.<\/p>\n

Microsoft Power Platform offers to extract data from any kind of document (see Improve business performance with AI Builder<\/a>) and a reference document automation pipeline (see Get started with AI Builder document automation<\/a>).<\/p>\n

Implementing such a solution is usually an iterative \u00a0journey which could be summarized in 4 phases :<\/p>\n

1. Building the initial AI model
\n2. Prototyping
\n3. Initial rollout in production
\n4. Mature production<\/p>\n

Build the initial AI model<\/h1>\n

During this phase, a champion (commonly named as \u201cmaker\u201d) with some technical background, will train an AI model <\/strong>using samples from the most common documents received to assess wherever the AI technology is able to properly extract data from these samples.<\/strong><\/p>\n

Select samples<\/h3>\n

To start, the maker should gather at least 5 sample documents for each document layout to process. The AI model will use these samples to learn how to extract the desired data. Usually, documents coming from different suppliers have different layouts.<\/p>\n

The form processing model currently supports up to 200 collections which should in theory handle up to 200 suppliers. Given that there is a limited number of documents generating software, it’s likely that several suppliers will provide similar layout which could be extracted by the same collection.<\/p>\n

This will be fine-tuned during the prototyping and initial production phase (see Prototyping section in this article ).<\/p>\n

\"\"<\/p>\n

For each provider sample, the maker will identify which fields data and which table data must be extracted by the AI model.<\/p>\n

\"\"<\/p>\n

\u00a0<\/p>\n

Use the training wizard<\/h3>\n

Now that the maker has gathered sample documents and has identified the fields and tables to extract, the next action is to create a new Form Processing model (see Create a form processing model<\/a>). The first step of the training wizard is to define the fields to define in the \u201cFields\u201d tab:<\/p>\n

\"\"<\/p>\n

And the tables in the \u201cTables (preview)\u201d tab<\/p>\n

\"\"<\/p>\n

The maker will define one collection per layout, so one per supplier.<\/p>\n

\"\"<\/p>\n

The combined file size of the documents used for training per collection must not exceed 50 megabytes (MB), and PDF documents shouldn’t have more than 500 pages (see Requirements and limitations<\/a>).<\/p>\n

Test the model<\/h3>\n

After going through the model tagging and training, the model is ready to be tested. The maker will use the \u201cQuick test\u201d to check that the data is properly extracted.<\/p>\n

\"\"<\/p>\n

When necessary, the maker will use the \u201cEdit model\u201d to improve the performance by providing more samples or retagging (see Improve the performance of your form processing model<\/a>).<\/p>\n

Once satisfied, the maker can publish the model (see <\/em><\/strong>Train and publish your form processing model<\/em><\/strong><\/a>) and is now ready to step into prototyping.<\/em><\/strong><\/p>\n

Prototyping<\/h1>\n

During this phase, the maker will setup the document automation pipeline to adapt it to his business needs and will test it with selected documents. <\/strong><\/p>\n

The maker will setup the pipeline provided with Power Automate document automation base kit<\/strong> by configuring the previously created model to handle new documents received (see Configure the document automation base kit<\/a>).<\/p>\n

The result of the extraction is stored in Dataverse (see What is Microsoft Dataverse?<\/a>) and manually reviewed in the document automation application<\/strong> by the maker.<\/p>\n

This data can be manually imported to the target system or the maker can build an export flow.<\/p>\n

The state of all documents entering the pipeline can be monitored in the document automation application. <\/strong><\/p>\n