- Pointer
- Posts
- Issue #701
Issue #701
Essential Reading For Engineering Leaders
Tuesday 24th March issue is presented by Unblocked
Stop babysitting your coding agents. Unblocked gives them the organizational knowledge to generate mergeable code without the back and forth.
It pulls context from across your engineering stack, resolves conflicts, and cuts the rework cycle by delivering only what agents need for the task at hand.
— Charles-Axel Dein
tl;dr: “Most management questions can be answered by "it depends" and "I know it when I see it". A couple of weeks ago a peer asked me "how do you know when to step in and give directions as a manager?" My first hunch was to reply "based on my experience (and many mistakes)”.”
Leadership Management
— Sharif Shameem
tl;dr: “It feels like there's something like a conservation law at work here: the amount of stupidity you're willing to tolerate is directly proportional to the quality of ideas you'll eventually produce.”
CareerAdvice
— Dennis Pilarinos
tl;dr: Coding agents rarely produce mergeable code on the first try. Even with rules, skills, and MCP connections, you still end up babysitting each session, supplying missing context, fixing wrong assumptions, and burning tokens. What do we need to do to actually give AI tools the understanding they need?
Promoted by Unblocked
Tools Agents
— Lara Hogan
tl;dr: I spoke with a number of staff and principal engineers at various companies who are using AI daily to do their work, and are feeling pretty effective at it... My goal in interviewing them was to validate an idea I’ve been developing: that what teams might benefit from right now is a regular touchpoint with their team in which tips, tricks, and other “aha” moments about how their work is evolving are shared. I detail how to do this below!
Leadership Management
“Control your own destiny or someone else will.”
— Dunya Kirkali
tl;dr: “The following three strategies transform the interview from a test of memory or raw problem-solving into an evaluation of how candidates leverage modern tools while applying genuine expertise.”
Leadership Management
tl;dr: Are you still prompting one agent at a time? That's so 2025. Intent is a developer workspace for orchestrating multiple agents from a living spec. Go from idea to PR without juggling terminals, repo copies, or stale prompts. It's free with Claude Code / Codex / OpenCode.
Promoted by AugmentCode
Tools Agents
— Avery Pennarun
tl;dr: “I know what you're thinking. Come on, 10x? That’s a lot. It’s unfathomable. Surely we’re exaggerating. Nope. Just to be clear, we're counting “wall clock time” here rather than effort. Almost all the extra time is spent sitting and waiting.”
Management CodeReview
— Shilpa Kannan, Frances Coronel
tl;dr: “Dozens of deep technical threads, many with 100+ replies, guided this project. These weren’t quick bug fixes but rather architecture decisions requiring tight alignment across product, design, frontend, backend, and mobile engineers.”
Architecture
— Michael Lopp
tl;dr: “I’ve never built more interesting, random, and useless scripts, tools, and services than I have in the last six months. The cost to go from “Random Thought” to “Working Something” has never been lower... The following is a set of tools and practices I’ve gathered over the last 90 days, which continue to accelerate my process and give me daily joy.”
Tools
Most Popular From Last Issue
The Future Of Software Engineering With Anthropic - Akash Bajwa
Notable Links
Browser Use: AI browser agent.
Electrobun: Build fast, tiny, cross-platform desktop apps.
Pentagi: Automated security testing.
TerminalUse: Infra for background agents.
TradingAgents: LLM financial trading framework.
How did you like this issue of Pointer?1 = Didn't enjoy it all // 5 = Really enjoyed it |