9 Deployment and management

 

This chapter covers

  • Tracking changes to your AI assistant over time
  • Managing multiple versions of your assistant
  • Safely deploying code to production

The day Fictitious Inc. decided to build a conversational AI assistant was the happiest day of John Doe’s life. John, a developer at Fictitious Inc., could not wait to get started building. He raced ahead of the rest of his project team, spending nights and weekends developing the assistant. John’s project team was happy about his enthusiasm, but nobody on the team was exactly sure what John was up to all the time.

Communication with John was a struggle. He was slow to respond to instant messages and emails. Occasionally a team member would walk to John’s desk find him furiously typing new code on his workstation. They would ask John how the latest feature was going, and John would give a lengthy soliloquy. By the time the team member got back to their own desk, they had forgotten what John told them.

9.1 Where to store your code

 
 
 
 

9.1.1 Taking the Wild West approach

 
 
 
 

9.1.2 Using source control for code

 

9.2 Where to run your code

 
 

9.2.1 Development environment

 
 
 
 

9.2.2 Test environment

 
 
 

9.2.3 Production environment

 
 
 

9.2.4 After the first production deployment

 

9.3 Using source control for other assets

 
 
 

Summary

 
 
 
sitemap

Unable to load book!

The book could not be loaded.

(try again in a couple of minutes)

manning.com homepage
test yourself with a liveTest