diff --git a/app/priv/blog/engineering/2026/10-02-delayed-gratification-in-ai-summer.md b/app/priv/blog/engineering/2026/10-02-delayed-gratification-in-ai-summer.md
new file mode 100644
index 0000000..c94483a
--- /dev/null
+++ b/app/priv/blog/engineering/2026/10-02-delayed-gratification-in-ai-summer.md
@@ -0,0 +1,39 @@
+%{
+  title: "Delayed Gratification in AI Summer",
+  author: "Willem van den Ende",
+  tags: ~w(AI ComprehenstionMaxxing CollaborationMaxxing),
+  description: "I made a prototype and let it sit for over two months. why? attention is all i need - focus can be frustrating, because i can't do the other things, but it is also what lets me enjoy holidays and get good results out of my work.",
+  published: true
+}
+---
+
+AI augmentation is often great. I can scale up the [wishful thinking](https://www.qwan.eu/2021/07/01/tdd-wishful-thinking.html) and explore more with working, well tested, software at my fingertips. Instant gratification, what is not to like? Well, that working software does not mean anything if I can't explain it to other people. 
+
+![Near Allemond, France. View on Lac du Verney. A row of trees in the foreground, an expansive lake in the middle, trees and mountains to the left and right of the lake, a stream appears above the lake in the distance.](/images/blog/2026/allemond-view-on-lac-du-verney.jpeg)
+_Allemond, a View on Lac du Verney ©️ Willem van den Ende_
+
+I made a prototype and let it sit for over two months. 
+
+Why? [Attention is all I need](https://en.wikipedia.org/wiki/Attention_Is_All_You_Need). Focus can be frustrating, because I can't do the other things, but it is also what lets me enjoy holidays and get good results out of my work with clients. I might do some reading, and put some likes on other peoples posts, but authoring blog posts and software doesn't appear to be a good fit just yet. Single tasking, and having the occasional chat on some of the paused ideas seems to be possible.
+
+In addition to focus to work on bigger ideas, I also need to be able to explain them to other people. [Chris Matts](https://papachrismatts.uk/) told me that when he blogs a lot, a good blog post needs conversations with at least four different people before it could turn into something publishable. It appears to work that way for me as well.
+
+After writing [Swim the Test](/blog/engineering/swim-the-test) I made a prototype for an **app playground**, where I, or a stakeholder, can click through an application workflow, assuming different roles at each step of the process. 
+
+I even wrote a draft blog post about that playground back then. I forgot all about that draft until just now, when I looked through my drafts for the first time in a few months. So this focus thing seems to work ;-). That playground, and what I see as its' mechanics are going to be their own post, but also then I was delaying gratification, at a smaller scale. This is what I wrote the week after Swim the Test as we had friends staying over, and our kids had started their summer holiday:
+
+> It is nice to be able to make progress while having friends over. I have learned to not multi-task too much. When a question is too big to answer by prompting a coding agent on my phone, I will just percolate on it. Good designs come from working on them - [you have to work for creativity to happen](https://philosiblog.com/2014/07/02/inspiration-exists-but-it-has-to-find-you-working/), and from stepping away from the screen and coming back with a fresh perspective.
+
+It is great being able to continue work from my phone, with a coding agent I host on a server elsewhere. It helps me finish threads I started during the day while doing the school run. But I (attempt to) put it away to focus on those around me. I do have a bias to action, but letting ideas simmer is not optional, especially when it comes to a cohesive user experience, and creating ideas that spread.
+
+I had a very busy September (not complaining) and am considering picking up some other software ideas from last year. But the workflow playground comes first, because a lack of clarity in my mind about what the workflows around e.g. a team in a collaborative board app added so much friction that it was easier... to start on something else, and delay the gratification maybe too much.
+
+Focus is great, but it has to find you focusing! 
+
+## Further Reading
+
+[AI Winter](https://en.wikipedia.org/wiki/AI_winter) on Wikipedia
+
+[Swim the Test](/blog/engineering/swim-the-test)
+
+[Choosing a System Metaphor](http://www.extremeprogramming.org/rules/metaphor.html) often takes iteration. Work, building, co-creating, explaining to wider audiences, flailing, coming back to it and eventually finding something. I saw the *playground* metaphor floating around again. It does seem to fit, and aligns with [Swift Playgrounds](https://developer.apple.com/swift-playground/) and earlier the [Pharo Playground](https://github.com/pharo-open-documentation/pharo-wiki/blob/master/General/Playground.md). Only in my playground, we author a sequence of events that have a visual, swim the test style, flow as "Reviewable representation". More about that later, perhaps.
diff --git a/app/priv/static/images/blog/2026/allemond-view-on-lac-du-verney.jpeg b/app/priv/static/images/blog/2026/allemond-view-on-lac-du-verney.jpeg
new file mode 100644
index 0000000..873beb4
Binary files /dev/null and b/app/priv/static/images/blog/2026/allemond-view-on-lac-du-verney.jpeg differ