In this episode, our guest discusses the complexities and challenges faced while integrating AI features into enterprise products like Miro. Seva Brekelov, a principal engineer at Miro, tells the stories about GDPR compliance, security, and bureaucratic obstacles, as well as overcoming technical issues with moderation and data storage. Learn about the journey from initial discussions to deploying AI-powered features such as image generation, summarization, and custom diagramming, all while addressing limitations and pre-prompting. Tune in to discover insights on the significance of legal consultations, different implementation strategies, and the future of AI in enterprise settings. Find the insights about growing as an engineer with the help of AI too!
00:00 Introduction and Initial Challenges
00:24 The Journey Begins: Meeting the CPO
01:32 Navigating Security and Legal Hurdles
03:22 Implementing Moderation and Overcoming Technical Issues
08:39 AI Features and Their Applications
14:14 Technical Deep Dive: Under the Hood
19:15 Challenges and Solutions in AI Integration
23:29 Streaming and WebSocket Challenges
37:01 Final Thoughts and Advice for Developers
39:46 Conclusion and Call to Action
#ai #openai #softwaredevelopement #softwareengineering
Moderation:
https://learn.microsoft.com/en-us/azu...
Azure OpenAI:
https://azure.microsoft.com/en-us/pro...
Miro AI features appendum:
https://miro.com/legal/ai-features-ad...
SEE instead of WebSocket:
https://developer.mozilla.org/en-US/d...
October 8 Miro Canvas24 announcement:
https://canvas24.miro.com/
Code Widget: / why-we-developed-a-code-block-widget-in-miro
Code Widget 2: / the-miro-code-block-widget-an-approach-bac...
Code block: https://help.miro.com/hc/en-us/articl...
Mapping and diagramiing: https://help.miro.com/hc/en-us/articl...
Business Oriented System Design Course: https://vvsevolodovich.dev/business-o...
Patreon: / vvsevolodovich