The author shares an experience of building a JIRA integration and provides an example of an app that allows users to interact with a currency exchange rate API in natural language. The author emphasizes the power of open-source models, which allow organizations to keep sensitive data on-premises, customize models for specific use cases, avoid vendor lock-in, and meet regulatory requirements. The article concludes by outlining emerging patterns in AI engineering, including rapid prototyping in user-friendly interfaces, exporting to version-controlled specifications, applying traditional DevOps practices, and iterating based on automated testing and deployment.
Key takeaways:
- The bridge between rapid prototyping and production-ready AI applications is a critical aspect of the transformation in AI engineering.
- Production systems need to be declarative, version-controlled, and reproducible, but they can also be accessible.
- The AI engineering process involves rapid prototyping in user-friendly interfaces, exporting to version-controlled specifications, applying traditional DevOps practices, and iterating based on automated testing and deployment.
- Open source models allow organizations to keep sensitive data on-premises, customize models for specific use cases, avoid vendor lock-in, and meet regulatory requirements.