Issue #717
Essential Reading For Engineering Leaders
Tuesday 19th May’s issue is presented by turbopuffer
Reduce Your Vector Database Bill By 90%+
Agents are only as good as the context they can retrieve. If they miss a doc, they miss the answer. turbopuffer is a fast search engine that makes every byte searchable at a fraction of the cost of traditional vector databases. Cursor, Cognition, and Notion run retrieval on turbopuffer.
⚡ p90 latency: 8ms
💸 1M docs for under $5/month
🔎 Vector, full-text, regex, and metadata search
Search Every Byte For 10x Less →
I’m An Introvert. This Is How I Get Myself To Speak Up.
— Wes Kao
tl;dr: “Prepare go-to phrases to insert yourself in meetings, ask a colleague to keep you accountable, and other tactics I personally use to get myself to speak up.”
CareerGrowth Communication
Distilling Leadership Wisdom
— James Stanier
tl;dr: “This month, we’re going to explore a practical technique for learning from leaders you’ll never have access to: distilling their thinking into an AI role you can query on demand.”
Leadership AI CareerGrowth
Reduce Your Vector Database Bill By 90%+
tl;dr: “Agents are only as good as the context they can retrieve. If they miss a doc, they miss the answer. turbopuffer is a fast search engine that makes every byte searchable at a fraction of the cost of traditional vector databases. Cursor, Cognition, and Notion run retrieval on turbopuffer.”
Promoted by turbopuffer
Scale Database Infrastructure
How I Use LLMs As A Staff Engineer In 2026
— Sean Goedecke
tl;dr: “A year ago I would very occasionally ask an agent to make changes to a single file if it was a simple change I couldn’t be bothered typing out. Sometimes I would copy a function I wrote into a LLM chat window for feedback. But now I start every single change by asking an agent to solve the problem, and usually push the PR after a single editing pass.”
Staff+ Productivity AI
“Computers are good at following instructions, but not at reading your mind.” — Donald Knuth
Learning Software Architecture
— Alex Kladov
tl;dr: Alex argues that the real skill isn’t technical design but understanding how social incentives shape code. He illustrates this with rust-analyzer. Your codebase will mirror your organization’s incentive structure whether you design for it or not.
Architecture CareerGrowth
AI Is Writing Code Faster Than Ever, But Who Checks It?
tl;dr: When speed is prioritized over reliability, technical debt and security risks accumulate silently. To realize the full ROI of AI, organizations must shift from manual reviews to an automated verification layer. Evaluate your next vendor with: (1) Six evaluation pillars for modern code review. (2) Strategies to solve the AI productivity paradox. (3) A comprehensive checklist for code health.
Promoted by Sonar
Guide CodeReview AI
Interrogatory LLM
— Martin Fowler
tl;dr: “When we need an LLM to perform a complex task, we often need to feed it a lot of context. Coming up with a design for a new feature requires descriptions of how we want the feature to appear to the user, guidelines on how it should be implemented, information on external systems to consult, and so on. All this can be several pages of markdown. The obvious way to do this is for a human to write this context, but an alternative is to use an LLM to write this context after interviewing a human.”
Productivity AI
I Don’t Think AI Will Make Your Processes Go Faster
— Frederick Vanbrabant
tl;dr: “I have the feeling that every organization out there is, at least partially, focusing on process optimization, something that often happens when the market is down. These days there is also the AI angle to the entire thing, and the unrealistic expectations that follow it.” Frederick shares why throwing AI at a current process doesn’t have impact until you solve the upstream issues.
Management Business AI
Using An Engineering Notebook
— Nicole Tietz-Sokolskaya
tl;dr: “One of my core software engineering practices is writing, by hand, in a physical notebook. It’s one of the most important things I do to remain productive and effective. Maybe the single most important. And it’s a practice that I see very few others using!”