- Pointer
- Posts
- Issue #715
Issue #715
Essential Reading For Engineering Leaders
Tuesday 12th May’s issue is presented by Unblocked
Unblocked turns code, docs, tickets, and conversations into actionable context, so engineers move faster and agents stay on track.
— Anna Shipman
tl;dr: Anna identifies three principles she considers non-negotiable for any executive making AI decisions today: (1) AI is non-deterministic: you’re managing probabilities, not certainties. (2) The economics have flipped: it’s no longer about what you build, but what you buy and what that costs you long-term. (3) Competitive advantage is in integration: how you embed AI matters far more than which AI you use.
Leadership Strategy AI
— Molly Graham
tl;dr: “It’s so hard to realize this when you’ve built your career and your brand on caring, but the person who takes everything personally, who needs things to turn out a specific way — that person isn’t more invested than everyone else. They’ve just lost their objectivity. And objectivity is what you actually need to make good decisions.”
Leadership Management
— Dennis Pilarinos
tl;dr: For agents to work at scale, they need to deeply understand how your team works. Rules, skills, and separate MCPs give access to information, but not understanding. Read how Unblocked built a context engine that gives agents what they need to generate mergeable code the first time.
Promoted by Unblocked
Agents DeveloperProductivity
— Rahul Garg
tl;dr: “The practices that make human pair programming effective - onboarding, structured design discussion, shared standards - apply equally to working with AI coding assistants. I propose five patterns that bring this collaborative scaffolding to AI-assisted development, shifting the experience from correcting a tool to collaborating with a capable teammate.”
DeveloperProductivity BestPAI
“Control your own destiny or someone else will.”
— Jake Handy
tl;dr: A field guide to the 'slop cannon' - the engineer running multiple AI agents in parallel, shipping huge PRs they can't explain, and confusing velocity for progress. Jake includes a manager's checklist for spotting the pattern and practical fixes for managing such developers.
Managements Agents AI
— Victoria Krauchunas
tl;dr: Enterprise SSO might feel complicated, but it's one of the simplest ways to win trust and close deals faster. Most customers won't even say the words 'Enterprise SSO'. They'll ask if you support Okta, or SAML, or SCIM syncing. This guide decodes what they're really asking, so you can answer with confidence and stop losing deals to acronyms you don't quite recognize.
Promoted by PropelAuth
Security Guide
— Murat Demirbas
tl;dr: There are two kinds of "abstraction" conflated under the same umbrella term. (1) Modularity abstraction: This is the traditional abstraction taught in CS curricula as ADTs, APIs, layered design, etc. It is all about encapsulation, drawing boundaries, and hiding internals. (2) Modeling abstraction: This is the same sense of abstraction mathematicians and physicists when building models for thinking and reasoning. The goal is to find the minimal and most elegant description that preserves the property you care about.
SystemDesign DeepDive
— Will Keleher
tl;dr: “But I think there are some nuggets of knowledge that are particularly valuable and don’t require a lot of supporting mental infrastructure. You don’t need to know any python to use python3 -m http.server to start a simple server in a directory, but it might still make your work marginally easier.” Will shares a few examples.
DeveloperProductivity
— Bassim Eledath
tl;dr: “That gap doesn't close overnight. It closes in levels. 8 of them. Most of you reading this are likely past the first few, and you should be eager to reach the next one because each subsequent level is a huge leap in output, and every improvement in model capability amplifies those gains further.”
Agents Guide
Editorial Note
A quick roundup of other articles that I found interesting and relevant to engineering leaders:
The 2026 AI Index Report coins the term the “jagged” frontier of AI, which I find useful. AI can’t reliably tell the time but can win a gold medal at the International Mathematical Olympiad.
Kevin Kelly, founder of Wired Magazine, says the 10 hour interview with Claude about its existence is “one of the most remarkable conversations I have ever had.”
Mythos by Anthropic is likely more marketing stunt than super AI. Mythos found one low priority vulnerability in curl, underwhelming the open source team.
According to Price Law, the square root of the number of people in a domain does 50% of the work. Once you see this, it can be leveraged into effective leadership strategy.
Thank you for the few folks that shared Programming Still Sucks, an enjoyably sardonic essay that lays greed as the root cause of the the tech industry’s dysfunction.
Most Popular From Last Issue
How To One-On-One - Ben Balter
Notable Links
Financial Services: Anthropic’s financial toolkit for common workflows.
Floci: OS local AWS emulator.
Hunk: Review-first terminal diff viewer.
Manifest: Reduce your AI costs.
Mirage: Unified virtual file system for AI agents.
How did you like this issue of Pointer?1 = Didn't enjoy it all // 5 = Really enjoyed it |