It works. It is also too big.
Part five. HC-01 is running in a real humidor: 522 logged samples, agreement with an independent hygrometer, and one closed control loop.
· 6 min read
Blog
notes from the bench
Building AI agent systems and hardware prototypes: the review gates that check them, and the boards, firmware and enclosures they check. Real builds, real measurements.
The probe said OPEN. The display was working.
Part four. My J5 continuity probe reported OPEN on a board whose display was provably working, and a bring-up flag shipped on the demo unit.
· 6 min read
The annular-ring fix held: five of five boards work
Part three. Same design, one inverted flag put back, a different assembler. Five of five rev E boards flashed, drove the display and read the sensor.
· 8 min read
The agent guessed a sensor's size. We built a mount around a part that doesn't exist.
You cannot prompt a model out of guessing. You can make the guess fail a gate: require a provenance field and reject any number without one.
· 4 min read
Our QA agent reported zero interference. The part had a hole in it.
An interference check measures overlap between solids. It cannot see material that was never there — so it passes a part with a wall missing.
· 4 min read
The third reviewer has to be blind
Hand an agent your hypothesis and it hands the hypothesis back, confirmed. The only review worth running is one that never saw the first two.
· 4 min read
We corrected 3.0 mm to 3.175 mm. The calipers read 2.925.
Our spec said 1/8 inch Baltic birch is 3.175 mm. Correct arithmetic on a wrong label. The stock measured 2.925, and the groove was built on the error.
· 6 min read
ESP32-S3 enclosure design: give the antenna its 15 mm
Espressif asks for at least 15 mm of clearance around an ESP32-S3's PCB antenna inside the housing. What that means for a 3D-printed case, with sources.
· 6 min read
We told the fab the missing annular rings were intentional. They weren't.
Part two. The fab asked about one thing before building. We said it was deliberate. It was a parser bug, and it explains the open display headers.
· 8 min read
What a 3D-printed prototype enclosure actually costs in 2026
Filament is under half a percent of the bill. Here's the itemized total for a palm-sized ESP32 enclosure, design time included.
· 10 min read
From 3D-printed enclosure to injection molding: when to switch
A single-cavity prototype steel tool for a palm-sized enclosure runs about $10k — we've had our own parts quoted. Here's the break-even math on when it pays.
· 10 min read
STEP vs STL: which file your enclosure design actually needs
STL is a triangle mesh. STEP is real CAD geometry. Converting one direction is routine; the other throws away everything you'd want to change later.
· 11 min read
Custom PCB fabrication: three of five boards arrived dead
Three of five boards arrived dead and two had open joints. Test points found where power stopped, and later showed the open joints were our fault.
· 6 min read
From jumper wires to a custom PCB: building the HC-01 humidor controller
An ESP32 rat's nest became a four-revision custom board. The most expensive mistake was a sensor we never actually measured.
· 4 min read