​📍This month, Christine Seeman is giving a talk: AI Loves Design Patterns (Too Much). Nick Nisi will also give a short talk on how he made a Fruit Fly review his code (seriously)!

​👏 Special thanks to Improving for hosting Nebraska JS at their offices and for sponsoring the food.

​​​​​Schedule

• ​5:30PM - arrive - eat food - network

• ​6:00PM - Talk 1 Starts

• ​6:40PM - Talk 2 Starts

• ​~7:30PM - optional Beer JS for continued discussion at The Hill

​​​​​Talk 1 Summary (Christine)

​AI Loves Design Patterns (Too Much).

​AI coding tools love design patterns: a Factory for one object, a Strategy for an if/else, a Builder for three parameters. You'd think smarter models would grow out of it. They haven't. In 2026, the vendors' own docs warn their newest models over-engineer, and research shows more capable models write more bloated code, not less. This talk walks through real AI output, the red flags that give it away, why the pattern reflex happens, when the AI is actually right, and the prompts and rules files that steer it back to simple. Sometimes the best pattern is no pattern at all.

Short version, AI Loves Design Patterns (Too Much):

AI still over-engineers in 2026: Factories for one object, Strategies for an if/else. Even the vendors warn about it. Learn the red flags, why it happens, when the pattern is right, and the prompts that steer AI back to simple. Sometimes the best pattern is no pattern at all.

​Talk 2 Summary (Nick)

​I Made a Fruit Fly Review My Code

​Code is being written faster than ever, and Nick Nisi, who leads developer and agent experience at WorkOS, argues that the human reviewer is now the bottleneck. To make the point, he hooked a simulated fruit fly brain, built from a full scan of its neurons, up to code review: AI turns each change into literal "code smells," sugar and bitter rewards teach the fly what good and bad code taste like, and it was right about 88% of the time in testing. Then he plays a live round against the audience and lays out a practical plan where team review skills, classifiers and automated reviewers only send the risky pull requests to a human, backed by proof like screenshots and smoke tests.

​​​​Notes

​Join the Discord to stay up to date on future events or discuss past ones.

​If you are interested in speaking at a future event, feel free to message either Nick Nisi or Kevin Van Cott on the Discord or LinkedIn.

​As always, whether speaking or attending at Nebraska JS, please follow our Code of Conduct