Learnings: Summaries of PowerPoint Presentations with AI and PowerAutomate

In the modern business world, PowerPoint presentations are indispensable for efficiently conveying information and impressively presenting ideas. In this post, I explore how the integration of artificial intelligence (AI) and Power Automate can facilitate the automated processing and summarization of presentations. I share valuable insights, experiences, and challenges that arose during this process.

Project Goal: Automated SharePoint Summaries

The main goal of our project was to use Power Automate to automatically process PowerPoint presentations and transfer concise summaries to a SharePoint list. However, this process proved to be more complex than initially thought.

Problems with Text Recognition A significant obstacle was the lack of a direct function in Power Automate for extracting content from PowerPoint files. Our solution was to export the presentations as PDF and use the AI Builder action “Recognize text in an image or a PDF document”. Despite the extraction, the result was chaotic, as every single letter was captured. Many slides contained irrelevant content like screenshots or sponsor logos, making the creation of meaningful summaries difficult.

Search for Effective Solutions

To improve the results, we tested the “Async Extractive Summarization (2022-10-01-preview)” action from Azure Cognitive Services. Unfortunately, these results were also unsatisfactory, as the generated summaries were insufficient and the “Key Phrases (V3.0)” function didn’t add value in terms of key concepts.

AI Technology and PowerPoint: Progress Required

Our experiment clearly shows that the currently available AI technology for the automatic creation of PowerPoint summaries is not yet mature. None of the tested tools could meet our requirements. Other methods or manual adjustments are needed to generate high-quality summaries.

Conclusion

Our endeavor to use AI and Power Automate for creating PowerPoint summaries did not lead to the desired results. It’s important to recognize the limits of automation. Often manual interventions or alternative strategies are required, with human judgment continuing to be of crucial importance.