~/lodehed/blog 10 entries
back to ~/lodehed
jesper@lodehed $ ls ./posts --sort=time

Writing

Notes from the practice. Mostly about agentic development, codebase archaeology, and what twenty years has taught me to stop saying out loud. Filed in reverse chronological order. No newsletter.

filter
  1. 2026-05-055 min read
    Auto-dream is the right idea. The implementation isn't there yet.
    A memory feature that prunes itself while you sleep is exactly what long-running agents need. The version that briefly shipped in Claude Code can also delete files without telling you, and silently stop running when it crashes. I want it back, with better manners.
    #claude-code·#ai-agents·#memory
    read →
  2. 2026-04-226 min read
    Stop hiring for AI fluency. Hire for codebase fluency.
    The people shipping with agents in 2026 aren't the ones who can spell MCP. They're the ones who can read a five-year-old codebase in an afternoon and tell you which migration is keeping the team awake.
    #hiring·#agents·#practice
    read →
  3. 2026-04-098 min read
    What I actually do in Claude Code, by the hour.
    An honest log of one Saturday on Jobado: when I drove, when I steered, when I had three agent sessions running at once. Including the two times I had to undo the agent's work, and why I think that's still a win.
    #claude-code·#log·#jobado
    read →
  4. 2026-03-275 min read
    The migration is the product.
    AI accelerates the typing. It does not accelerate the judgment. Most senior work isn't building. It's the careful undoing of last year's correct decisions.
    #architecture·#migrations
    read →
  5. 2026-03-114 min read
    On owning the whole chain.
    Two versions of seniority. Both real. One is undervalued in 2026 hiring, and I want to make a small case for it.
    #career·#seniority
    read →
  6. 2026-02-247 min read
    Lovio's Saturday test.
    Wedding-planning SaaS has a strange constraint: most failure modes are tolerable Monday morning. The one on the wedding day is not. Building for that asymmetry changed how I think about availability.
    #lovio·#ops·#swedish
    read →
  7. 2026-02-095 min read
    The quiet staff engineer.
    The most senior engineer in a room is usually the calmest. They've been wrong enough times to know the cost of dramatic certainty.
    #practice·#career
    read →
  8. 2026-01-216 min read
    MCP is the boring layer. That's the point.
    Most of the value I get from MCP isn't novel agent capability. It's the same connect-and-call ergonomics every codebase has wanted from its IDE for fifteen years.
    #mcp·#agents·#tooling
    read →
  9. 2026-01-089 min read
    How I read a codebase in an afternoon.
    A pragmatic, ordered checklist. Where the trust lives, where the load-bearing decisions hide, and the three files that almost always tell you the truth about a team.
    #practice·#code-review
    read →
  10. 2025-12-228 min read
    Twenty years of shipping. Things I no longer believe.
    An end-of-year list. Not what's new, but what I've quietly stopped saying. Including 'we'll fix it later,' 'just one more abstraction,' and 'they'll read the README.'
    #career·#retrospective
    read →