- Pointer
- Posts
- Issue #716
Issue #716
Essential Reading For Engineering Leaders
Friday 15th May’s issue is presented by Gauntlet
Join Gauntlet instructors as they provide insight into Infrastructure for multi-agent applications. You bring the front and backend, and Anthropic handles the agentic sessions and environments.
We're going to build a web-based multi-agent multimedia UI for creatives. Stitching together prompts, models and Gen AI sessions with memory.
— Brian Houck
tl;dr: “In this study, we explore how AI is reshaping software engineering by analyzing survey data from over 1,300 developers and interviews with 22 AI-fluent practitioners. We specifically look at what developers want from AI and how AI fluency develops, and discuss three possible futures for the developer role.”
CareerGrowth DevEx AI
— Bruce Daisley
tl;dr: “Across decades of research, it turns the best predictor of team performance isn’t the talent of the team or whether it includes superstar individuals, but rather it’s the behaviour of the worst person. A bad apple really can ruin a team.”
Leadership Management Culture
tl;dr: Join Gauntlet instructors as they provide insight into Infrastructure for multi-agent applications. You bring the front and backend, and Anthropic handles the agentic sessions and environments. We're going to build a web-based multi-agent multimedia UI for creatives. Stitching together prompts, models and Gen AI sessions with memory.
Promoted by Gauntlet
Event AI
— Subbu Allamaraju
tl;dr: Aviation faced the same automation debates we're having now about AI in software engineering - cognitive surrender, rising entropy in codebases, and productivity perception gap. Despite these challenges and shrinking team sizes, the author argues there's a playbook worth borrowing for engineering leaders.
Leadership Management AI
"If you never fail, your aren't trying hard enough"
— Eugene Yan
tl;dr: “How can we work effectively with AI? What’s the workflow, how does it scale, and how do we improve our systems over time? And ideally, it should compound. Every finished artifact—code, docs, analysis, decisions—becomes context for the next session. And each correction updates a config that reduces future errors. While I’m still learning, I’ve repeated my answers often enough that I’m writing it here so the next time I’m asked I can share a link instead.”
Guide AI Productivity
— Amy Carrillo Cotten
tl;dr: Fifteen years ago, conference talks sold engineering leaders on microservices as a universal fix. The same hype cycle is now running on AI. What microservices got wrong - and why recognizing the pattern early is how you avoid paying for it later.
Promoted by Uplevel
Leadership AI Architecture
— Jenni Nadler
tl;dr: Jenni covers what makes both good and bad error messages. For bad error messages, she gives cites: inappropriate tone, technical jargon, passing the blame and generic messages that have no reason. Good messages say what happened and why, provide reassurance, are empathetic, help the user fix the issues if possible and provide a "way out" e.g. a contact number.
Product CaseStudy
— Adam Rogal, Adam Yarger
tl;dr: Over the last few months, we've been rolling out a code review agent across DoorDash's engineering org. The central challenge turned out to be attention: helping the agent focus on the parts of a change that deserve review, and stay quiet when it has nothing useful to add. The bar we set for ourselves wasn't "does it find things." It was: (1) Do engineers actually change their code when it comes up with a comment? (2) Does it preserve enough trust that teams keep it enabled?
CaseStudy CodeReview AI
— Saicharan Nimmala
tl;dr: “When responding to code review comments, responses like “Done,” “Updated,” or “Fixed” are commonly used to indicate addressing a suggestion. However, sometimes, a little extra context adds a lot of clarity.”
Management CodeReview Tips
Null Pointer
Monitored Autonomy
Most Popular From Last Issue
The 8 Levels Of Agentic Engineering - Bassim Eledath
Notable Links
Agentic Inbox: Self-hosted email client with an AI agent.
Agent Skills: Production-grade engineering skills for coding agents.
CloakBrowser: Chromium that passes bot detection.
Coral: One SQL interface over APIs, files, and live sources.
Tools: Small, low stakes and low effort tools.
How did you like this issue of Pointer?1 = Didn't enjoy it all // 5 = Really enjoyed it |