Issue #712
Essential Reading For Engineering Leaders
Friday 1st May’s issue is presented by Unblocked
Stop Babysitting Your Agents
Unblocked is the context engine your coding agents are missing. It pulls from your team’s code, conversations, and docs to surface the right context for every task, so agents stay on track without the set up tax or the correction loops.
How To Be Direct And Strategic
— Yue Zhao
tl;dr: “I saw an issue with a process on my team recently and brought it up directly in a team meeting a few days later. I was very direct about the problem, gave all the details, and explained how it impacted everyone. To my surprise, my manager shut it down completely, and now I cannot get any buy-in from anyone. What happened? Where did I do wrong?”
Leadership Communication
Drunk Post: Things I’ve Learned As A Senior Engineer
— Kirill Bobrov
tl;dr: “A few years ago, a data engineer got drunk and wrote down everything he learned in 10 years of engineering. The original account is deleted, but the post captures something real — the kind of honesty you only get after a few glasses of wine. Preserving it here, typos and all.”
CareerGrowth BestPractices Entertaining
[Webinar] How To Stop Babysitting Your Agents
tl;dr: “Agents can generate code. Getting it right for your system is the hard part – you end up wasting time and tokens in the back and forth. More MCPs solve access but not understanding. Join us for a FREE webinar on May 6 to see how to give agents exactly what they need to generate mergeable code the first time.”
Promoted by Unblocked
AI Agents Events
Speak In The Affirmative: “Do This” Versus “Don’t Do That”
— Wes Kao
tl;dr: “It’s to your benefit to be as clear as possible when you speak or write, because clear communication helps you get what you need. One way to do this is to speak in the affirmative, rather than the negative... If you speak in negatives, your recipient has to take an extra mental step.”
Leadership Management Communication
“It’s not that I’m so smart, it’s just that I stay with problems longer.” — Albert Einstein
How I Use AI To Code
— Chris Parsons
tl;dr: A practitioner’s guide to AI-assisted coding in 2026. Senior engineers should shift from reviewing AI-generated diffs to training the harness that produces them via CLAUDE.md files, skill files, and feedback loops. The bottleneck has moved from code generation to verification.
AI Guide BestPractices
How Engineering Leaders Are Actually Using AI To Improve Software Quality
tl;dr: “Most teams aren’t struggling with whether to use AI, they’re struggling with how to use it well. At Breakpoint, speakers like Jason Huggins (creator of Selenium), Keith Klain, Ashley Hunsberger, and many more cover the real decisions quality engineering leaders are facing: how to scale AI across your org, where agentic and autonomous QA workflows actually deliver, and what it takes to move past the pilot. If you’re figuring out where AI fits in your engineering process, this is a practical starting point, May 12–14.”
Promoted by BrowserStack
AI Event
Structured-Prompt-Driven Development
— Wei Zhang, Jessie Jie Xia
tl;dr: “Instead of relying on ad hoc chats, SPDD turns prompts into assets that can be: version controlled, reviewed, reused, and improved over time. Teams use structured prompts to capture requirements, domain language, design intent, constraints, and a task breakdown. Then the LLM generates code within a defined boundary, so output becomes more predictable and easier to validate.”
AI Guide BestPractices
Email Is Crazy
— Saurabh Khawase
tl;dr: “Email evolved organically over the years, tracing its origins to the academic labs of ARPANET in the ‘70s. Its various components were designed by different people, at different times, facing different challenges. The email ecosystem is a very complex beast with more than 100 RFCs mandating its various protocols.” A deep dive into how email works under the hood.
Infrastructure DeepDive
How To Make A Fast Dynamic Language Interpreter
— Fil Pizlo
tl;dr: “This post is about optimizing an extremely simple AST-walking interpreter for a dynamic language called Zef that I created for fun to the point where it is competitive with the likes of Lua, QuickJS, and CPython.”