Running agents in parallel turned engineers into notification processors. Defending focus is a losing fight. The job now is making interruptions affordable: visible signals, no friction, finished work you can walk away from, and more valuable work within reach.
Documentation rots, and what your product does ends up in a few developers' heads. So I stopped writing docs and started extracting them: small, typed, linked notes pulled from the codebase, written for product, with every claim traced back to the line it came from.
Most agentic pipelines chase throughput by taking humans out of the loop. Better products come from small, isolated pipelines that raise quality at each human handover, from bug reports and refinement to pull requests and releases, whilst domain knowledge stays with people.
Fyxer's per-seat price more than doubled, so we built our own meeting notetaker in one night with Claude Code. A blind benchmark on our own bilingual meetings, EU-only storage, and a per-hour cost that puts the whole company below what nine Fyxer seats now cost.
When implementation becomes cheap, what's left? I stopped writing code, ventured into machine learning and 3D game development, and discovered that AI made me remarkably efficient at making mistakes. Fortunately, it also made me much faster at learning from them.
As a kid, your skills could only get you so far in a game. Sometimes the game itself was the problem. AI fixed a decades-old goalkeeper bug from a short video, and the real shift is what that means for anyone with an idea.
Git worktrees let you run agents in parallel, but every new worktree starts cold, fights over ports and leaves junk behind. Worktrunk wraps worktrees in a few simple commands and a hook system, so one config file gives the whole team warm, isolated environments that clean up after themselves.
AI has a confidence problem. Human intelligence was shaped by an uncertain world, and uncertainty is exactly the ingredient AI is missing.
The Android emulator was never the real cost. The setup was: SDK paths, JDK versions, licence acceptance, a hand-edited config file, repeated on every machine and every new joiner. Claude Desktop takes that off your hands, and the wait that's left is spent reading a plan, not a stack trace.
A back-end engineer set out to redesign a React app with an AI agent and came out actually knowing React. The unlock wasn't the prompting, it was understanding the code well enough to steer it. As the cost of entry collapses, knowing the technology matters more, not less.
Analytics only shows the events you remembered to add, never the ones you forgot. Let Claude instrument features as it builds them, then run a skill that audits your tracking against your own docs and live data, flagging what's missing, noisy, or quietly broken.
Integrating a tool with Claude rarely needs an MCP server. A boring script wrapped as a named, version-controlled skill does the job, and the real value shows up when two skills combine: one tool tells you what happened, another tells you why.
Writing code by hand used to be the job. Soon it will be a hobby, like woodworking or growing your own veg. What a company pays for now is judgment: knowing what to build, catching the answer that looks right and isn't, deciding when it's good enough to ship.
Coding agents made implementation cheap, but validation never got cheaper. That shift moves the bottleneck from writing code to deciding what is worth building, and the response is more autonomy and faster iteration, not more detailed upfront plans.
Using Claude Code as the orchestrator and Codex as the engine gives you the best of both tools: Claude's UI, Codex's depth, and minimal Claude token spend. The economics only work when the task is big enough to justify two layers.
