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. (1) p90 latency: 8ms. (2) 1M docs for under $5/month. (3) Vector, full-text, regex, and metadata search. Search Every Byte For 10x Less.

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

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!”

Productivity CareerGrowth

Editorial Note

Interesting reads also on my radar this week:

• “The Great Flattening” reports how organizations are restructuring by removing layers, with engineering management roles shifting into a coding-oriented lead / coach role. Coinbase reduced organizational layers below CEO / COO to five. From the CEO: “The future is small, high-context teams that can move quickly. Leaders will own much more, with as many as 15+ direct reports.”

• Augment Code recently published The State of AI-Native Engineering in 2026 report, which is worth a read. “Everyone is going “AI-native,” and nobody agrees on what that means“ is one of several contradictions the report cites.

• According to HBR, employees are turning to AI for career advice, emotional support, and even friendship at work, weakening interpersonal work relationships.

• I love this by Phil Eaton, former cofounder at TigerBeetle - a software internals book club covering topics in databases, distributed systems, and software performance.

Most Popular From Last Issue

The AI-Native Developer - Brian Houck

Notable Links

Agentmemory: Persistent memory for your agent.

Compozy: Drive the lifecycle of AI-assisted dev.

Dograh AI: OS voice agent platform.

Re_gent: Version control for agents.

Train Your GPT: Build a modern LLM from scratch.