Daily Reading List – July 21, 2026 (#829)

My team runs a program where we spend a week with a customer taking a use case from idea to MVP. The team (and customer) came to San Diego this week so that I could be part of the exercise. It’s super cool to watch a group come together quickly to iterate, learn, and ship.

[blog] Introducing Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber. Big model release day at Google. These are good performers, well-priced, and quite efficient with tokens.

[blog] Reliability Is Not a Feature. It Is a Discipline. It’s also not a vague “non-functional requirement.” It’s a way of working, as this post calls out.

[blog] How do you stay familiar with the code when it’s written by an LLM? Great post. There are smart ways (necessary ways?) to stay involved in the code that you’re ultimately accountable for.

[blog] Guide to AI Tokenomics: Eleven Principles for Token Efficient Software Engineering. We’re all figuring out what works best in this world where tokens aren’t free. I liked this advice.

[blog] The LLM Critics Are Right. I Use LLMs Anyway. Most smart people I know aren’t ignorant of the complaints or problems with LLMs. But that doesn’t mean LLMs aren’t still useful.

[article] Are PMs becoming irrelevant? The old PM role is mostly irrelevant, I agree. The advice here is to become a strategic PM (not an “AI PM”).

[article] How do you go from junior to staff engineer when AI writes the code? Maybe mentoring got easier. Keep hiring juniors, and bring agents into the mix to get them productive.

[article] Frontline Workers Know How to Solve Your Organization’s Biggest Problems. It makes no sense to me to be a disconnected executive who only spends time with other execs. You should be talking with your employees multiple times per day.

[blog] How to structure a log. Maybe AI can help you even if your logs are a mess. But create good logs is the right hygeine regardless.

[blog] 13 hands-on demos to build on Gemini Enterprise Agent Platform. Great stuff. Here’s a list of tutorials you can run to learn how to build, scale, govern, and optimize agents. Each category matters.

[article] 2030-shaped software. Some good thoughts here about agents, UIs, and what we’ll be using in a few years.

[blog] In-House LLM Serving at Netflix. What breaks at scale? Those are some of the most interesting things to learn from others.

Want to get this update sent to you every day? Subscribe to my RSS feed or subscribe via email below: