/EdgeLog ยท Essays
Essays
28 pieces, 3 axes, 5 series. Every claim carries a number.
Series NeuroTerm 2 published
01 Why I Started Building NeuroTerm 02 How I Keep Speed, Quality and Intent with AI Agents Series harness-maker 2 published
01 Side vs Production 02 Intent-Based Development Series Tuned 5 published
01 What I Am Making, and Why I Make It Alone 02 The Co-Founder That Built Too Fast 03 A Roadmap That Marks Where to Quit First 04 The Two Seats Left to People 05 What I Don't Hand Off to My AI Team Series AI-Written Firmware 4 published · 1 upcoming
01 What I Didn't Tell It 02 What Breaks Outside the Function 03 Measuring the Gap With 233 Tests 04 What to Hand Over, Where to Stop It 05 Introducing the Verification Gate
Series AI Agents in Embedded 3 published
01 The Spec-Driven TDD We Put Off 02 Learning Context Engineering 03 Opening the Full Pipeline 11 standalone essays
- 01 Philosophy 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?
- 02 Philosophy I Don't Know My Philosophy Yet I spent years building whatever the requirements said. Making my own products, I found I needed a philosophy. I have none yet, so I write to find it.
- 03 Methods How Many AI Code Reviews Is Enough? I spent 400 LLM calls on one codebase to learn this. One review pass finds 34% of the real defects, and the four most-repeated findings were all false.
- 04 Methods 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.
- 05 Methods 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.
- 06 Methods 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.
- 07 Methods The CRA Begins: Embedded Software's Center of Gravity Moves September 11, 2026: the EU Cyber Resilience Act's first duty applies. I see it less as compliance than as embedded engineering's center of gravity moving.
- 08 Methods AI Finally Needs Hardware Engineers In 2026 inference overtook training. The edge is where it grows fastest, and the work left there, I think, is the work AI cannot do.
- 09 Methods Offline Datasheet RAG: The Pipeline I Argued Against I argued against RAG for hardware docs, then an offline job made me build one. What survived: SVD parsing, structural chunks, hybrid search, multi-query.
- 10 Methods 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.
- 11 Making Why I Started EdgeLog I wanted to know what happens when LLMs, zero-trust security, and modern frameworks meet real embedded hardware. A research log from the edge.