AI Drafted the Docs. Your Job Is Decisions, Not Prose.
AI Drafted the Docs. Your Job Is Decisions, Not Prose. When a language model drafts documentation, the bottleneck shifts from writing to reviewing,…
Latest News
⚑ Report a ProblemTech news from the best sources
All topics
AI
Gear
News
Tech
agents
ai
api
architecture
automation
beginners
career
database
devchallenge
devops
javascript
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
react
security
showdev
testing
tutorial
typescript
webdev
I was solving agent portability at the wrong boundary
Copying the last repo's agent setup into a new one worked at first. It also copied product-specific assumptions. Once I had several active projects,…
The Docs Draft Pipeline: What an AI May Write and What You Must Own
The most common documentation failure is not a weak prompt or a lazy writer; it is the absence of a clear boundary between machine-draftable content…
Opinion: Your Tests Can't See What a Migration Destroys — Dry-Run It on a Clone
Opinion: Your Tests Can't See What a Migration Destroys — Dry-Run It on a Clone A green test suite is the wrong tool for judging an AI-generated mig…
The pipeline was green. The product was underspecified
The checks all passed. I still would not have sent the resume. I had been using a Cursor agent to implement a private facts → prose resume generator…
Linter Blocks Code Merge Over Minor Formatting: Solution to Streamline Review Process for New Developers
Introduction: The Linter Dilemma Imagine this: you’re a developer, new to the game, and you’ve just spent hours crafting a piece of code. It works f…
From 40 AI Tools to 4: A Practical Framework for Choosing What You Actually Need
I have installed at least 40 AI tools on my phone over the past year. The ones I actually use every day? Fewer than eight. After three months of tri…
Model Routing Made My AI Agents Cheaper. It Didn't Make Them Easier to Trust.
I spent a while optimizing what my AI agents cost to run. Cheap models for routine work. Better models when the task actually needed them. That made…
Resolve Open Questions: a /qa Skill for Claude Code
By @atwellpub , GBTI Network Member . Originally published on gbti.network . Claude Code loads any markdown file at .claude/skills/<name>/SKIL…
Multi-tenant SaaS on a .NET workflow engine, without restarting to onboard a customer
The most expensive restart in SaaS is often the one nobody planned: onboarding a new customer. Every SaaS team expects adding a tenant to be a datab…
My Claude Code Skills in Production: What the Audit Taught Me
A Claude Code skill is a Markdown file you drop into ~/.claude/skills/ . It describes a complete workflow: when to trigger it, how to execute it ste…
The Verification Ladder: A Field Guide
Claude has, at various points in our working relationship, warmly endorsed: an efficiency statistic fabricated over one too many turns of a massive…
They Asked for My AI Rules. But I Could Not Just Hand Them Over.
A team lead announces that the team will start using AI-assisted development. Everyone nods. Nobody asks what that actually means on Monday morning.…
I fixed my AI reviewer. Then I kept solving the wrong problem
I've been building an AI-assisted editorial pipeline for technical writing. Notion cards become markdown drafts in the repo, pass through review, th…
Fixing tmux dashboard for coding agents: Mobile Clipboard + 30%
This article was originally published on BuildZn . Everyone talks about managing LLMs but nobody explains how to babysit them in CLI. Juggling 3+ tm…
Workflow Series (06): Security — Cross-Step Injection Propagation and Four Defense Principles
Workflow Security vs Skill Security Skill security (Skill Series Article 02) protects a single call : can user input hijack this Skill's behavior? W…
Workflow Series (05): Evaluation Framework — Three-Layer Testing and Trace Tracking
Why Workflows Need a Dedicated Evaluation Framework Traditional software testing covers code correctness. Workflows add two layers of uncertainty: L…
anything i can imagine
thesis ai is great at helping me make anything i can imagine. if i can picture the answer, the process, or the steps ahead of time, the model can us…
Adding one field to Notion cost me 2.5 hours. The same change in Tana took 30 seconds.
Adding a single property to a live Notion database with 160 rows isn't a five-minute job — it's a backfill session. I learned this the hard way in w…
I audited 340 reading captures. Only 20% ever became knowledge I actually used.
Out of 340 captures over 90 days — Readwise highlights, Obsidian quick-captures, browser bookmarks — exactly 68 ever became a note I actually used.…
Shelved Projects #1: Windows Automata
Welcome to the first post of my new series, "Shelved Projects" . In this series, I dig into the digital attic to share projects that were technicall…
cursor automations for housekeeping and hygiene
quick answer cursor automations are a good fit for recurring housekeeping and hygiene tasks that already have a clear definition of done. i currentl…
73% of my context switches came from one mistake: sharing a workspace across two businesses
73% of my context switches last year traced back to a single root cause — not bad habits, not weak discipline, but a Notion dashboard that mixed ad…
I tagged 34 decision notes in Obsidian over 18 months. Reading them back broke my Notion setup.
34 tagged decision notes. That's all it took to realize my Notion database was lying to me. I run three revenue streams — ad ops automation, two nic…
GitHub Actions adds a background marker, and the linear job stops being the only shape
A small word that changes the rhythm of a job For as long as I have been writing Actions workflows I have been carrying a quiet workaround in my hea…
My 7-step prompt chain failed silently at step 6. Here's what replaced it.
A manual checkpoint outperformed full automation by 35 percentage points. That's the number that changed how I build every prompt chain now. I spent…
I tracked every async writing block for 90 days. Output nearly doubled — but not how I expected.
Switching from Obsidian-first drafting to Claude-first drafting nearly doubled my usable words per 90-minute block: from ~420 to ~780. That number s…
My second brain cost me 140+ hours before it saved me anything
35 minutes of daily maintenance, compounded over 8 months, is north of 140 hours — and I didn't see that number anywhere in the glowing 'second brai…
My weekly review clocked 14 minutes median — here's the one structural change that made it stick
Obsidian prompts beat open-ended reflection every time: median review time across 6 weeks was 14 minutes, fastest was 9, slowest was 22 (and that we…
When Code Takes a Break: What Engineers Think About on Silent Days
📌 Overview Today was a "silent day" — no Claude Code sessions, no commits, no code changes. Yet technical work isn't just about writing code. This d…