Chapter 10. From AI Assistant to AI Engineer: The Future of AI in Software Development
Now that you understand the AI-enabled SDLC and how you can leverage AI assistants in your workflow today, let’s take it a step further. This chapter ventures into a near future where AI agents can complete software engineering tasks autonomously; we refer to this evolution of the AI agent as the AI engineer.
At this point, you may wonder what the difference is between an AI assistant and an AI engineer, as the assistant can also complete certain tasks autonomously (e.g., “Document this code”). The key difference is the ability to handle more complex, custom tasks requiring analysis, planning, making decisions, and potentially changing multiple artifacts.
With an AI assistant, as discussed in earlier chapters of this book, the human is tightly integrated into the process and effectively delegates microtasks to the assistant. The software developer requests specific tasks (e.g., “Document this function,” “Generate unit tests,” “Refactor this code”) and reviews each incremental change made by the AI.
In contrast, when working with an AI engineer, the expectations are that the human engineer delegates larger tasks to the AI engineer (e.g., “Add a coupon discount flow to our checkout process”) and that the AI engineer completes this task from start to finish, similar to a human engineer. The workflow evolves from depending on a close human feedback loop to a more general delegation of tasks. However, ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access