EdgeLogby
Making Methods Philosophy
About
EN / KO
← All Tags

#ai-agents

20 posts

  • How I Keep Speed, Quality and Intent with AI Agents

    I build NeuroTerm, an embedded terminal, alone with Claude Code and Codex. Written intents and a two-week release train keep speed, quality and intent.

    Nov 1, 2026 · 8 min read
  • Why I Started Building NeuroTerm

    My agents could not see the board's serial console, so I carried the logs. NeuroTerm takes over that job and keeps up as the technology changes.

    Oct 30, 2026 · 4 min read
  • Making What I Don't Fully Understand

    I don't fully understand the products I make. We always used things we couldn't see into, for reasons we trusted. As those reasons fade, what remains?

    Oct 26, 2026 · 5 min read
  • harness-maker: Intent-Based Development

    I write down my product's job and principles, then return to them each time I choose, specify and judge a feature. Notes from my tennis product, Tuned.

    Oct 4, 2026 · 8 min read
  • LLM PCB Routing: What I Learned From a Human's Fixes

    I handed a 96% auto-routed PCB to a contract engineer. He redrew finished routes, not only the last 4%. I kept that difference as 16 rules for my agent.

    Aug 9, 2026 · 16 min read
  • harness-maker: Side vs Production

    I run side and production projects together, and they need different workflows. Most harnesses are fixed, so I built a tool that makes one per project.

    Aug 7, 2026 · 4 min read
  • Tuned: What I Don't Hand Off to My AI Team

    An AI team writes most of my first drafts. The parts I must know and the parts I decide, I still understand to the end. Read wide, write in one lane.

    Jul 12, 2026 · 5 min read
  • Tuned: The Two Seats Left to People

    I re-sorted the twenty-eight disciplines a hardware product needs. Twenty end as files, so the harness took them. Six stop at a doorway. Two stay human.

    Jul 6, 2026 · 6 min read
  • Tuned: A Roadmap That Marks Where to Quit First

    A solo founder's roadmap is closer to a map of kill-gates than a schedule. Cheap, decisive checkpoints before costly stages, and permission to quit early.

    Jun 13, 2026 · 5 min read
  • Tuned: The Co-Founder That Built Too Fast

    The harness made building so cheap I built most of the product before checking anyone would pay. A good co-founder's risky side, a solo founder's trap.

    Jun 12, 2026 · 4 min read
  • Tuned: What I Am Making, and Why I Make It Alone

    A tennis player and 18-year embedded engineer builds an impact sensor alone, with an LLM as the team. Page one of a productization diary, kept either way.

    Jun 11, 2026 · 3 min read
  • How Long Does Harness Engineering Have?

    Everything useful in a harness ends up absorbed into vanilla. What survives is what the vendor structurally will not or cannot build. Notes on the shift.

    Jun 6, 2026 · 2 min read
  • What loop would keep my software improving with LLMs?

    A hypothesis I am still sorting out: whether I can wire my own project to LLMs and turn it into a loop that keeps improving itself.

    May 16, 2026 · 10 min read
  • AI-Written Firmware: What to Hand Over, Where to Stop It

    3-Tier Trust sorts PRs, then verification gates (spec, TDD, RAG, HIL, deterministic analyzer, more) take them to merge. Each catches its own defect class.

    Apr 25, 2026 · 7 min read
  • AI-Written Firmware: What Breaks Outside the Function

    AI-written firmware breaks where a single function can't show it. I found 3 patterns visible in the diff and 3 that only surface after 49 days.

    Apr 9, 2026 · 8 min read
  • AI-Written Firmware: What I Didn't Tell It

    A junior wrote a logging daemon with an AI tool. It passed my review, ran fine, and later wore out an eMMC. The risk was in what the prompt left out.

    Apr 4, 2026 · 5 min read
  • AI Agents in Embedded: Opening the Full Pipeline

    I open one AI-agent-built i.MX8M Plus sensor driver project, folder by folder: specs, property tests, review agents, and feedback loops.

    Mar 15, 2026 · 10 min read
  • AI Agents in Embedded: Learning Context Engineering

    AI agents wrote good Yocto recipes but silently corrupted sensor data and misconfigured SPI registers. What fixed it was the context I gave them.

    Mar 14, 2026 · 9 min read
  • AI Agents in Embedded: The Spec-Driven TDD We Put Off

    Embedded teams skipped TDD for its cost. With AI agents I watched that math change. Notes on testing a Yocto IMU driver from a spec, with JSON feedback.

    Mar 13, 2026 · 9 min read
  • Hardware Docs for LLMs: Why I Went Back to grep

    RAG cut the cross-references that make hardware docs useful. After wrestling with a pipeline, I went back to handing the LLM my SVD and PDF as file tools.

    Mar 9, 2026 · 9 min read
/SUBSCRIBE ยท EMAIL

The notebook, by email

Products made alone, with AI, plus the measurements and failures behind each call. Biweekly, no spam.

Unsubscribe anytime.

Or subscribe via RSS.
HomeMakingMethodsPhilosophyAboutAll essays
© 2026 EdgeLog·made by
GitHub·Email·NeuroTerm·RSS