AI is already part of the engineering toolbox. The next challenge is using it deliberately.

In this highly interactive session, we will explore what it means to treat AI usage as an engineering discipline. That starts with choosing the right tool, model, and level of reasoning for the task instead of automatically reaching for the most capable option.

But good decisions require visibility. We will demonstrate a token usage dashboard and a token counter tool we have built to capture usage across our engineering tools, and explore what the data can tell us about model choice, cost, efficiency, and engineering behavior.

The goal is not to use less AI. It is to understand what we use, why we use it, and whether we are using the right intelligence for the job.

Delivery Options:
- Duration: 20-45 minutes (flexible)
- Language: English
- Level: Inspiration (100-200)

Audience:
The talk can be adjusted to target either developers or managers.