- Pointer
- Posts
- Issue #740
Issue #740
Essential Reading For Engineering Leaders
Friday 7th August’s issue is presented by Gauntlet
Watch anytime · Free · New sessions added regularly
Night School is Gauntlet's free education series on what AI-native work actually looks like — no hype, no vendor pitches, just engineers and operators showing how they really build. The full library is now available on demand, so you can watch any session whenever you want.
Go deep on planning, specs, and decision logs that separate AI engineers from vibe coders. See how a team ships go-to-market work with AI in the loop, how to build any MCP you want, and how to make a real game with AI-generated art and no dev background. Every session is a practical, over-the-shoulder look at how AI changes the work — recorded and ready to watch on your schedule.
Inside the library:
Hands-on sessions across engineering, go-to-market, product, and design — not generic AI overviews
Real toolchains and workflows the Gauntlet team uses every day, walked through step by step
Practical takeaways you can apply to your own projects the same week
New sessions added as the series continues, so the library keeps growing
— Wes Kao
tl;dr: (1) What does this person know? What’s new for them? (2) Why are we doing this? (3) What do they need in order to do this task? (4) What does great look like? (5) What’s the timeline and priority level? (6) What’s most likely to go wrong? What can I do to prevent this from happening?
Management Delegation Tips
tl;dr: “When managers are under pressure, and especially when they’re under pressure to retain a high performer, overpromising is one of the most common tools to reach for. The industry is rife with promises that someone will get a promotion, a new role, a large bonus, 5 more days of vacation, or any number of goodies, large or small.”
Management Retention DifficultConversations
tl;dr: Night School is Gauntlet's free education series on what AI-native work actually looks like — no hype, no vendor pitches, just engineers and operators showing how they really build. The full library is now available on demand, so you can watch any session whenever you want. Go deep on planning, specs, and decision logs that separate AI engineers from vibe coders. See how a team ships go-to-market work with AI in the loop, how to build any MCP you want, and how to make a real game with AI-generated art and no dev background. Every session is a practical, over-the-shoulder look at how AI changes the work — recorded and ready to watch on your schedule. Inside the library: (1) Hands-on sessions across engineering, go-to-market, product, and design — not generic AI overviews. (2) Real toolchains and workflows the Gauntlet team uses every day, walked through step by step. (3) Practical takeaways you can apply to your own projects the same week. (4) New sessions added as the series continues, so the library keeps growing.
Promoted by Gauntlet
AI Video
— Jade Rubick
tl;dr: “I’d like to share my favorite way of measuring the value delivery of engineering organizations. It’s something I’ve used at a lot of companies. I call it the ValueSum metric.”
Management Metrics
"Character is simply habit long continued"
— Yew Jin Lim
tl;dr: “In a meta study involving 177 studies and more than 22,000 people, researchers found that being anxious reliably predicts worse performance on various measures, including working memory, which is the part of your mind that does the processing, the reasoning, and the problem solving.”
Productivity Wellbeing
tl;dr: AI tools move too fast for unpinned local setups. Teammates pull different binary versions and dependency trees, and things break silently. Flox lets you pin your entire AI coding environment, from Claude Code and Copilot to CUDA dependencies. Your assistant knows exactly what's installed, and every engineer runs the exact same setup.
Promoted by Flox
Tools+Setup DevEx AI
— Tom Moertel
tl;dr: “To the extent that your programming language lets you express these things naturally in your logic, you should do so. But don’t contort your logic to accommodate intent and “why” information that would be easier for your audience to understand in natural language.”
Communication CodeQuality
— Bruno Gonçalves
tl;dr: “In this post we upgrade every piece of our basic harness toward that production shape, without hiding any of the mechanics behind a framework. The guiding question for the whole exercise is a simple one: How do you turn a single LLM call into a reliable system that can plan, act, recover, and prove it did the right thing?”
DeepDive AI Agents
— Michael Lynch
tl;dr: “I’ve written design docs as a developer at Google, Microsoft, and within my own companies. The specifics vary, but the underlying principles remain the same. A design doc should articulate the hard problems you’re solving and help your teammates give you feedback. Below, I share my approach to creating effective design docs and explain what belongs in a design doc and what does not.”
KnowledgeManagement Guide
Null Pointer
Downsizing
Most Popular From Last Issue
My Agentic Coding Setup, July 2026 - Domenic Denicola
Notable Links
Computer: Give your agent a computer.
LoopX: Local control plane for long-running agent work.
OpenWiki: Writes & maintains documentation.
PDF Inspector: PDF classification and text extraction.
Superfile: Modern terminal file manager.
How did you like this issue of Pointer?1 = Didn't enjoy it all // 5 = Really enjoyed it |