Issue #725

Essential Reading For Engineering Leaders

June 16th, 2026

Tuesday 16th June’s issue is presented by turbopuffer

Good context is the difference between an AI agent that can move mountains and an agent that is frustratingly dumb. That’s why Cursor, Notion, and Atlassian use turbopuffer to connect AI to data. Thanks to turbopuffer’s object-storage-native design, you can index far more data, and retrieve just the right context at inference time.

  • Up to 95% cheaper than traditional search engines

  • 8ms p50 query latency on 10M documents

  • Virtually infinite scalability on object storage

— Andi Roberts

tl;dr: “Research consistently supports this. People are influenced not only by the strength of an argument but also by trust, credibility, relationship, and perceived relevance. Before people commit to an initiative, they need confidence in both the message and the messenger. They need to feel understood before they feel persuaded. And they need to feel ownership before they feel commitment.”

Leadership Influence CareerGrowth

— Yue Zhao

tl;dr: “Your manager’s view of your performance is critical, but insufficient at senior levels in securing a specific rating. What becomes more important is that your performance is well understood by all the broader organization and teams you don’t regularly collaborate with, especially those who might hold outsized influence in the business.”

Staff+ PerformanceReviews

tl;dr: Good context is the difference between an AI agent that can move mountains and an agent that is frustratingly dumb. That’s why Cursor, Notion, and Atlassian use turbopuffer to connect AI to data. Thanks to turbopuffer’s object-storage-native design, you can index far more data, and retrieve just the right context at inference time. (1) Up to 95% cheaper than traditional search engines. (2) 8ms p50 query latency on 10M documents. (3) Virtually infinite scalability on object storage. Build your agent’s context layer for 95% less.

Promoted by turbopuffer

AI Agents

— Charity Majors

tl;dr: “But value is backed by durability, not disposability, and I don’t see that changing. Bits are cheap and fast and governed by the rules of logic and language, but anything with value must ultimately resolve with physical systems: persistence on the one side, user experience on the other.”

AI CodeQuality IndustryTrends

Editorial Note

I’m looking for software engineers who are currently managing or leading a team to answer one question over email.

If you are interested, click reply.

— Louise Deason

tl;dr: “Here are nine questions that have served me well. Some of them are diagnostic. Some of them are trapdoors. All of them have, at one point or another, told me something the company did not realise they were telling me.”

InterviewAdvice

tl;dr: AI agents are generating massive pull requests without context on your architecture, your standards, or your existing codebase. That's how architectural debt compounds 2.8x faster than code-level debt. Sonar was named a Leader in the 2026 Gartner® Magic Quadrant™ for Technical Debt Management and placed highest of all vendors on Ability to Execute. See how Sonar placed by reading the report. Download the report.

Promoted by Sonar

AI TechDebt

— Sergii Gorbachov

tl;dr: Agent-driven end-to-end (E2E) tests add a new exploratory layer to testing, but should they replace traditional deterministic tests? We ran more than 200 agentic E2E workflows in test workspaces using non-production data to find out how agentic testing could fit into both our and your testing stacks.

CaseStudy AI Testing

— Salvatore Sanfilippo

tl;dr: “The idea is to create a markdown file where an AI agent is asked to work as a QA engineer, performing a number of manual testings on the new release. For instance, in the case of DwarfStar (an inference engine for open weights LLMs) I use the following approach. In the markdown file, the agent is asked to check what are the new commits on top of the already released version of the software project. Then the model is told a list of things that should be performed.”

AI Agents Testing

— Ben Maraney

tl;dr: “Run a two-week program in which everyone across R&D could get experience building an agent. The hope was that this hands-on experience would get us all planning for the future and help us build good intuition about where and how to use AI agents. We had only five weeks to prepare the infrastructure they’d be using, and we needed it to serve everyone from veteran coders to recently hired analysts with very limited technical background.”

CaseStudy AI Agents

Flue: Agent harness framework.

Kage: Shadow any website for offline viewing.

Ktx: The context layer for data agents.

Novu: OS comms infrastructure for agents and products.

Openhuman: Personal AI super intelligence.

How did you like this issue of Pointer?

1 = Didn't enjoy it all // 5 = Really enjoyed it
1  |  2  |  3  |  4  |  5

Login or Subscribe to participate in polls.