These are my notes on Kent Beck: Software Engineering in the Age of AI | Prodacity 2026 | YouTube
A note about giving presentations: (At least for the first few times the presentation is given) Tell the audience that if anybody has a question, please raise your hand, and ask right away, rather than sit there thinking about it instead of following the presentation, or waiting for things to make sense later in the presentation, or asking a question at the end.
Introduces the term Augmented Development - Quote: "because to me, this is still a human process."
Introduces the term Genie - Quote: "I call it the Genie because it grants your wishes but it ends up being not what you really wanted."
He points out shortcomings of the Genie and recommends skepticism towards anything it produces.
Quote: "I absolutely love programming with the Genie."
Quote: "I have always had bigger ambitions than my technical skill could achieve and now I can try ridiculously ambitious projects and make a lot of progress." followed by: "I didn't say accomplish them."
Introduces the term "Futures" which, in my own words, is the inverse of Technical Debt (Entropy.) It is probably no coincidence that his first mentor, when he was fresh out of college, (which is a known fact but he also repeats it later in this talk,) was Ward Cunningham, the inventor of the term Technical Debt.
The idea is that we burn futures as we implement features, and if the futures reach zero you cannot add any more features. So, after implementing each feature we should work on replenishing the futures that we just burned. - Quote: "We are going to make some progress, and then we are going to consolidate'.
This ties in to A.I. because the features get developed very quickly, and therefore work on the futures must happen a lot more often.
So the challenge is how do you create this space between features, to go back and enhance the futures for the work that you are doing; and to do that in this environment where it is so tempting to just implement the next feature, the next feature, the next feature.
(Comment from the audience) By pacing yourself, you are giving yourself the chance to form an understanding. (With which Kent Beck fully agrees.)
Quote: "The best software that I have worked on is software where I try to maximize learning, which threw off software as a side effect. As opposed to I am trying to produce software and sometimes accidentally I learn something cause I messed up. If you are trying to maximize learning your habits look completely different."
Quote: "In the dark factory you don't learn anything --except in the end, you learn how unreliable the Genie really is."
Quote: "The distinction between one-shot development and iterative development": "There is such a temptation in spec driven development to go down the path of 'I am going to write a spec and the genie is going to produce the software, and if the spec is good enough then the software is going to be good enough.' And there is a word for that, that's exactly Waterfall Development, that did not work; it never worked."
Quote: "People will be amazed that Genie produced 200,000 lines of code. That's a measure of effort -- it has nothing to do with the mission."
Goodheart's Law: "When a measure becomes a goal, it ceases to be a measure".
His concluding statement, which is, unfortunately, very vague: "You have to find an expression of what you are trying to accomplish of the mission, that speaks to people's heads and their hearts, and then you have to repeat it; and then then that repetition, that not getting bored of how software development can be, over and over again, is part of the skill of leadership, to tell that same story as if it is brand new."